add scrapinglib
This commit is contained in:
Mathhew
3
scrapinglib/__init__.py
Normal file
3
scrapinglib/__init__.py
Normal file
@@ -0,0 +1,3 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from .api import search
|
||||
133
scrapinglib/airav.py
Normal file
133
scrapinglib/airav.py
Normal file
@@ -0,0 +1,133 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import json
|
||||
import re
|
||||
from lxml import etree
|
||||
from bs4 import BeautifulSoup
|
||||
from .parser import Parser
|
||||
from .javbus import Javbus
|
||||
|
||||
class Airav(Parser):
|
||||
source = 'airav'
|
||||
|
||||
expr_title = '/html/head/title/text()'
|
||||
expr_number = '/html/head/title/text()'
|
||||
expr_studio = '//a[contains(@href,"?video_factory=")]/text()'
|
||||
expr_release = '//li[contains(text(),"發片日期")]/text()'
|
||||
expr_outline = "string(//div[@class='d-flex videoDataBlock']/div[@class='synopsis']/p)"
|
||||
expr_actor = '//ul[@class="videoAvstarList"]/li/a[starts-with(@href,"/idol/")]/text()'
|
||||
expr_cover = '//img[contains(@src,"/storage/big_pic/")]/@src'
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number
|
||||
self.updateCore(core)
|
||||
|
||||
self.detailurl = 'https://cn.airav.wiki/video/' + number
|
||||
engine = Javbus()
|
||||
javbusinfo = engine.search(number, core)
|
||||
if javbusinfo == 404:
|
||||
self.javbus = {"title": ""}
|
||||
else:
|
||||
self.javbus = json.loads(javbusinfo)
|
||||
self.htmlcode = self.getHtml(self.detailurl)
|
||||
htmltree = etree.fromstring(self.htmlcode, etree.HTMLParser())
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def getNum(self, htmltree):
|
||||
# return super().getNum(htmltree)
|
||||
result = self.javbus.get('number')
|
||||
if isinstance(result, str) and len(result):
|
||||
return result
|
||||
number = super().getNum(htmltree)
|
||||
result = str(re.findall('^\[(.*?)]', number)[0])
|
||||
return result
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
title = super().getTitle(htmltree)
|
||||
result = str(re.findall('](.*?)- AIRAV-WIKI', title)[0]).strip()
|
||||
return result
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
result = self.javbus.get('studio')
|
||||
if isinstance(result, str) and len(result):
|
||||
return result
|
||||
return super().getStudio(htmltree)
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
result = self.javbus.get('release')
|
||||
if isinstance(result, str) and len(result):
|
||||
return result
|
||||
try:
|
||||
return re.search(r'\d{4}-\d{2}-\d{2}', str(super().getRelease(htmltree))).group()
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getYear(self, htmltree):
|
||||
result = self.javbus.get('year')
|
||||
if isinstance(result, str) and len(result):
|
||||
return result
|
||||
release = self.getRelease(htmltree)
|
||||
return str(re.findall('\d{4}', release)).strip(" ['']")
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_outline).replace('\n','').strip()
|
||||
|
||||
def getRuntime(self, htmltree):
|
||||
result = self.javbus.get('runtime')
|
||||
if isinstance(result, str) and len(result):
|
||||
return result
|
||||
return ''
|
||||
|
||||
def getDirector(self, htmltree):
|
||||
result = self.javbus.get('director')
|
||||
if isinstance(result, str) and len(result):
|
||||
return result
|
||||
return ''
|
||||
|
||||
def getActors(self, htmltree):
|
||||
b=[]
|
||||
a = super().getActors(htmltree)
|
||||
for v in a:
|
||||
v = v.strip()
|
||||
if len(v):
|
||||
b.append(v)
|
||||
if len(b):
|
||||
return b
|
||||
result = self.javbus.get('actor')
|
||||
if isinstance(result, list) and len(result):
|
||||
return result
|
||||
return []
|
||||
|
||||
def getCover(self, htmltree):
|
||||
result = self.javbus.get('cover')
|
||||
if isinstance(result, str) and len(result):
|
||||
return result
|
||||
return super().getCover(htmltree)
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
html_pather = re.compile(r'<div class=\"mobileImgThumbnail\">[\s\S]*?</div></div></div></div>')
|
||||
html = html_pather.search(self.htmlcode)
|
||||
if html:
|
||||
html = html.group()
|
||||
extrafanart_pather = re.compile(r'<img.*?src=\"(.*?)\"')
|
||||
extrafanart_imgs = extrafanart_pather.findall(html)
|
||||
if extrafanart_imgs:
|
||||
return extrafanart_imgs
|
||||
return ''
|
||||
|
||||
def getTags(self, htmltree):
|
||||
tag = []
|
||||
soup = BeautifulSoup(self.htmlcode, 'lxml')
|
||||
x = soup.find_all(attrs={'class': 'tagBtnMargin'})
|
||||
a = x[0].find_all('a')
|
||||
|
||||
for i in a:
|
||||
tag.append(i.get_text())
|
||||
return tag
|
||||
|
||||
def getSeries(self, htmltree):
|
||||
result = self.javbus.get('series')
|
||||
if isinstance(result, str) and len(result):
|
||||
return result
|
||||
return ''
|
||||
173
scrapinglib/api.py
Normal file
173
scrapinglib/api.py
Normal file
@@ -0,0 +1,173 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from scrapinglib.airav import Airav
|
||||
from scrapinglib.carib import Carib
|
||||
from scrapinglib.dlsite import Dlsite
|
||||
from scrapinglib.fanza import Fanza
|
||||
from scrapinglib.gcolle import Gcolle
|
||||
from scrapinglib.jav321 import Jav321
|
||||
from scrapinglib.javdb import Javdb
|
||||
from scrapinglib.mv91 import Mv91
|
||||
from .fc2 import Fc2
|
||||
from .madou import Madou
|
||||
from .mgstage import Mgstage
|
||||
from .javbus import Javbus
|
||||
from .xcity import Xcity
|
||||
from .avsox import Avsox
|
||||
|
||||
|
||||
def search(number, souces=None, proxies=None, dbcookies=None):
|
||||
"""
|
||||
TODO 支持更多网站 douban, imdb,tmdb anidb等
|
||||
type 区分 r18 与 normal
|
||||
"""
|
||||
sc = Scraping()
|
||||
return sc.search(number, souces, proxies=proxies, dbcookies=dbcookies)
|
||||
|
||||
|
||||
class Scraping():
|
||||
"""
|
||||
|
||||
只需要获得内容,不经修改
|
||||
|
||||
如果需要翻译等,再针对此方法封装一层
|
||||
不做 naming rule 处理,放到封装层,保持内部简介
|
||||
|
||||
可以指定刮削库,可查询当前支持的刮削库
|
||||
可查询演员多个艺名
|
||||
|
||||
参数:
|
||||
number
|
||||
cookies
|
||||
proxy
|
||||
sources
|
||||
TODO multi threading (加速是否会触发反爬？)
|
||||
|
||||
[x] translate
|
||||
[x] naming rule
|
||||
[x] convert: actress name/tags
|
||||
|
||||
"""
|
||||
|
||||
full_sources = ['avsox', 'javbus', 'xcity', 'mgstage', 'madou', 'fc2',
|
||||
'dlsite', 'jav321', 'fanza', 'airav', 'carib', 'mv91',
|
||||
'gcolle', 'javdb']
|
||||
func_mapping = {
|
||||
'avsox': Avsox().search,
|
||||
'javbus': Javbus().search,
|
||||
'xcity': Xcity().search,
|
||||
'mgstage': Mgstage().search,
|
||||
'madou': Madou().search,
|
||||
'fc2': Fc2().search,
|
||||
'dlsite': Dlsite().search,
|
||||
'jav321': Jav321().search,
|
||||
'fanza': Fanza().search,
|
||||
'airav': Airav().search,
|
||||
'carib': Carib().search,
|
||||
'mv91': Mv91().search,
|
||||
'gcolle': Gcolle().search,
|
||||
'javdb': Javdb().search,
|
||||
}
|
||||
|
||||
proxies = None
|
||||
dbcookies = None
|
||||
|
||||
def search(self, number, sources=None, proxies=None, dbcookies=None):
|
||||
self.proxies = proxies
|
||||
self.dbcookies = dbcookies
|
||||
|
||||
sources = self.checkSources(sources, number)
|
||||
json_data = {}
|
||||
for source in sources:
|
||||
try:
|
||||
print('[+]select', source)
|
||||
try:
|
||||
data = self.func_mapping[source](number, self)
|
||||
if data == 404:
|
||||
continue
|
||||
json_data = json.loads(data)
|
||||
except Exception as e:
|
||||
print('[!] 出错啦')
|
||||
print(e)
|
||||
# json_data = self.func_mapping[source](number, self)
|
||||
# if any service return a valid return, break
|
||||
if self.get_data_state(json_data):
|
||||
print(f"[+]Find movie [{number}] metadata on website '{source}'")
|
||||
break
|
||||
except:
|
||||
break
|
||||
|
||||
# Return if data not found in all sources
|
||||
if not json_data:
|
||||
print(f'[-]Movie Number [{number}] not found!')
|
||||
return None
|
||||
|
||||
return json_data
|
||||
|
||||
|
||||
def checkSources(self, c_sources, file_number):
|
||||
if not c_sources:
|
||||
c_sources = self.full_sources
|
||||
|
||||
sources = c_sources.split(',')
|
||||
def insert(sources,source):
|
||||
if source in sources:
|
||||
sources.insert(0, sources.pop(sources.index(source)))
|
||||
return sources
|
||||
|
||||
if len(sources) <= len(self.func_mapping):
|
||||
# if the input file name matches certain rules,
|
||||
# move some web service to the beginning of the list
|
||||
lo_file_number = file_number.lower()
|
||||
if "carib" in sources and (re.match(r"^\d{6}-\d{3}", file_number)
|
||||
):
|
||||
sources = insert(sources,"carib")
|
||||
elif "item" in file_number:
|
||||
sources = insert(sources,"getchu")
|
||||
elif re.match(r"^\d{5,}", file_number) or "heyzo" in lo_file_number:
|
||||
if "avsox" in sources:
|
||||
sources = insert(sources,"avsox")
|
||||
elif "mgstage" in sources and \
|
||||
(re.match(r"\d+\D+", file_number) or "siro" in lo_file_number):
|
||||
sources = insert(sources,"mgstage")
|
||||
elif "fc2" in lo_file_number:
|
||||
if "fc2" in sources:
|
||||
sources = insert(sources,"fc2")
|
||||
elif "gcolle" in sources and (re.search("\d{6}", file_number)):
|
||||
sources = insert(sources,"gcolle")
|
||||
elif "dlsite" in sources and (
|
||||
"rj" in lo_file_number or "vj" in lo_file_number
|
||||
):
|
||||
sources = insert(sources,"dlsite")
|
||||
elif re.match(r"^[a-z0-9]{3,}$", lo_file_number):
|
||||
if "xcity" in sources:
|
||||
sources = insert(sources,"xcity")
|
||||
if "madou" in sources:
|
||||
sources = insert(sources,"madou")
|
||||
elif "madou" in sources and (
|
||||
re.match(r"^[a-z0-9]{3,}-[0-9]{1,}$", lo_file_number)
|
||||
):
|
||||
sources = insert(sources,"madou")
|
||||
|
||||
# check sources in func_mapping
|
||||
todel = []
|
||||
for s in sources:
|
||||
if not s in self.func_mapping:
|
||||
print('[!] Source Not Exist : ' + s)
|
||||
todel.append(s)
|
||||
for d in todel:
|
||||
print('[!] Remove Source : ' + s)
|
||||
sources.remove(d)
|
||||
return sources
|
||||
|
||||
def get_data_state(self, data: dict) -> bool: # 元数据获取失败检测
|
||||
if "title" not in data or "number" not in data:
|
||||
return False
|
||||
if data["title"] is None or data["title"] == "" or data["title"] == "null":
|
||||
return False
|
||||
if data["number"] is None or data["number"] == "" or data["number"] == "null":
|
||||
return False
|
||||
return True
|
||||
78
scrapinglib/avsox.py
Normal file
78
scrapinglib/avsox.py
Normal file
@@ -0,0 +1,78 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Avsox(Parser):
|
||||
|
||||
source = 'avsox'
|
||||
imagecut = 3
|
||||
|
||||
expr_number = '//span[contains(text(),"识别码:")]/../span[2]/text()'
|
||||
expr_actor = '//a[@class="avatar-box"]'
|
||||
expr_actorphoto = '//a[@class="avatar-box"]'
|
||||
expr_title = '/html/body/div[2]/h3/text()'
|
||||
expr_studio = '//p[contains(text(),"制作商: ")]/following-sibling::p[1]/a/text()'
|
||||
expr_release = '//span[contains(text(),"发行时间:")]/../text()'
|
||||
expr_cover = '/html/body/div[2]/div[1]/div[1]/a/img/@src'
|
||||
expr_smallcover = '//*[@id="waterfall"]/div/a/div[1]/img/@src'
|
||||
expr_tags = '/html/head/meta[@name="keywords"]/@content'
|
||||
expr_label = '//p[contains(text(),"系列:")]/following-sibling::p[1]/a/text()'
|
||||
expr_series = '//span[contains(text(),"系列:")]/../span[2]/text()'
|
||||
|
||||
def queryNumberUrl(self, number):
|
||||
qurySiteTree = self.getHtmlTree('https://tellme.pw/avsox')
|
||||
site = self.getTreeIndex(qurySiteTree, '//div[@class="container"]/div/a/@href')
|
||||
self.searchtree = self.getHtmlTree(site + '/cn/search/' + number)
|
||||
result1 = self.getTreeIndex(self.searchtree, '//*[@id="waterfall"]/div/a/@href')
|
||||
if result1 == '' or result1 == 'null' or result1 == 'None':
|
||||
self.searchtree = self.getHtmlTree(site + '/cn/search/' + number.replace('-', '_'))
|
||||
result1 = self.getTreeIndex(self.searchtree, '//*[@id="waterfall"]/div/a/@href')
|
||||
if result1 == '' or result1 == 'null' or result1 == 'None':
|
||||
self.searchtree = self.getHtmlTree(site + '/cn/search/' + number.replace('_', ''))
|
||||
result1 = self.getTreeIndex(self.searchtree, '//*[@id="waterfall"]/div/a/@href')
|
||||
return "https:" + result1
|
||||
|
||||
def getNum(self, htmltree):
|
||||
new_number = self.getTreeIndex(htmltree, self.expr_number)
|
||||
if new_number.upper() != self.number.upper():
|
||||
raise ValueError('number not found in ' + self.source)
|
||||
self.number = new_number
|
||||
return new_number
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
return super().getTitle(htmltree).replace('/', '').strip(self.number)
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
return super().getStudio(htmltree).replace("', '", ' ')
|
||||
|
||||
def getSmallCover(self, htmltree):
|
||||
""" 使用搜索页面的预览小图
|
||||
"""
|
||||
return self.getTreeIndex(self.searchtree, self.expr_smallcover)
|
||||
|
||||
def getTags(self, htmltree):
|
||||
tags = super().getTags(htmltree).split(',')
|
||||
return [i.strip() for i in tags[2:]] if len(tags) > 2 else []
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
from .storyline import getStoryline
|
||||
return getStoryline(self.number)
|
||||
|
||||
def getActors(self, htmltree):
|
||||
a = super().getActors(htmltree)
|
||||
d = []
|
||||
for i in a:
|
||||
d.append(i.find('span').text)
|
||||
return d
|
||||
|
||||
def getActorPhoto(self, htmltree):
|
||||
a = super().getActorPhoto(htmltree)
|
||||
d = {}
|
||||
for i in a:
|
||||
l = i.find('.//img').attrib['src']
|
||||
t = i.find('span').text
|
||||
p2 = {t: l}
|
||||
d.update(p2)
|
||||
return d
|
||||
101
scrapinglib/carib.py
Normal file
101
scrapinglib/carib.py
Normal file
@@ -0,0 +1,101 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from urllib.parse import urljoin
|
||||
from lxml import html
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Carib(Parser):
|
||||
source = 'carib'
|
||||
uncensored = True
|
||||
|
||||
expr_title = "//div[@class='movie-info section']/div[@class='heading']/h1[@itemprop='name']/text()"
|
||||
expr_release = "//li[2]/span[@class='spec-content']/text()"
|
||||
expr_runtime = "//span[@class='spec-content']/span[@itemprop='duration']/text()"
|
||||
expr_actor = "//span[@class='spec-content']/a[@itemprop='actor']/span/text()"
|
||||
expr_tags = "//span[@class='spec-content']/a[@itemprop='genre']/text()"
|
||||
expr_extrafanart = "//*[@id='sampleexclude']/div[2]/div/div[@class='grid-item']/div/a/@href"
|
||||
expr_label = "//span[@class='spec-title'][contains(text(),'シリーズ')]/../span[@class='spec-content']/a/text()"
|
||||
expr_series = "//span[@class='spec-title'][contains(text(),'シリーズ')]/../span[@class='spec-content']/a/text()"
|
||||
expr_outline = "//div[@class='movie-info section']/p[@itemprop='description']/text()"
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number
|
||||
self.updateCore(core)
|
||||
|
||||
self.detailurl = f'https://www.caribbeancom.com/moviepages/{number}/index.html'
|
||||
htmlcode = self.getHtml(self.detailurl)
|
||||
if htmlcode == 404 or 'class="movie-info section"' not in htmlcode:
|
||||
return 404
|
||||
htmltree = html.fromstring(htmlcode)
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
return '加勒比'
|
||||
|
||||
def getActors(self, htmltree):
|
||||
r = []
|
||||
actors = super().getActors(htmltree)
|
||||
for act in actors:
|
||||
if str(act) != '他':
|
||||
r.append(act)
|
||||
return r
|
||||
|
||||
def getNum(self, htmltree):
|
||||
return self.number
|
||||
|
||||
def getCover(self, htmltree):
|
||||
return f'https://www.caribbeancom.com/moviepages/{self.number}/images/l_l.jpg'
|
||||
|
||||
def getTags(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_tags)
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
r = []
|
||||
genres = self.getAll(htmltree, self.expr_extrafanart)
|
||||
for g in genres:
|
||||
jpg = str(g)
|
||||
if '/member/' in jpg:
|
||||
break
|
||||
else:
|
||||
r.append('https://www.caribbeancom.com' + jpg)
|
||||
return r
|
||||
|
||||
def getActorPhoto(self, htmltree):
|
||||
# return super().getActorPhoto(htmltree)
|
||||
htmla = htmltree.xpath("//*[@id='moviepages']/div[@class='container']/div[@class='inner-container']/div[@class='movie-info section']/ul/li[@class='movie-spec']/span[@class='spec-content']/a[@itemprop='actor']")
|
||||
names = htmltree.xpath("//*[@id='moviepages']/div[@class='container']/div[@class='inner-container']/div[@class='movie-info section']/ul/li[@class='movie-spec']/span[@class='spec-content']/a[@itemprop='actor']/span[@itemprop='name']/text()")
|
||||
t = {}
|
||||
for name, a in zip(names, htmla):
|
||||
if name.strip() == '他':
|
||||
continue
|
||||
p = {name.strip(): a.attrib['href']}
|
||||
t.update(p)
|
||||
o = {}
|
||||
for k, v in t.items():
|
||||
if '/search_act/' not in v:
|
||||
continue
|
||||
r = self.getHtml(urljoin('https://www.caribbeancom.com', v), type='object')
|
||||
if not r.ok:
|
||||
continue
|
||||
html = r.text
|
||||
pos = html.find('.full-bg')
|
||||
if pos<0:
|
||||
continue
|
||||
css = html[pos:pos+100]
|
||||
cssBGjpgs = re.findall(r'background: url\((.+\.jpg)', css, re.I)
|
||||
if not cssBGjpgs or not len(cssBGjpgs[0]):
|
||||
continue
|
||||
p = {k: urljoin(r.url, cssBGjpgs[0])}
|
||||
o.update(p)
|
||||
return o
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
from .storyline import getStoryline
|
||||
result = getStoryline(self.number, uncensored=self.uncensored)
|
||||
if len(result):
|
||||
return result
|
||||
return super().getOutline(htmltree)
|
||||
|
||||
96
scrapinglib/dlsite.py
Normal file
96
scrapinglib/dlsite.py
Normal file
@@ -0,0 +1,96 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Dlsite(Parser):
|
||||
source = 'dlsite'
|
||||
imagecut = 4
|
||||
|
||||
expr_title = '/html/head/title/text()'
|
||||
expr_actor = '//th[contains(text(),"声优")]/../td/a/text()'
|
||||
expr_studio = '//th[contains(text(),"商标名")]/../td/span[1]/a/text()'
|
||||
expr_studio2 = '//th[contains(text(),"社团名")]/../td/span[1]/a/text()'
|
||||
expr_runtime = '//strong[contains(text(),"時長")]/../span/text()'
|
||||
expr_runtime2 = '//strong[contains(text(),"時長")]/../span/a/text()'
|
||||
expr_outline = '//*[@class="work_parts_area"]/p/text()'
|
||||
expr_series = '//th[contains(text(),"系列名")]/../td/span[1]/a/text()'
|
||||
expr_series2 = '//th[contains(text(),"社团名")]/../td/span[1]/a/text()'
|
||||
expr_director = '//th[contains(text(),"剧情")]/../td/a/text()'
|
||||
expr_release = '//th[contains(text(),"贩卖日")]/../td/a/text()'
|
||||
expr_cover = '//*[@id="work_left"]/div/div/div[2]/div/div[1]/div[1]/ul/li[1]/picture/source/@srcset'
|
||||
expr_tags = '//th[contains(text(),"分类")]/../td/div/a/text()'
|
||||
expr_label = '//th[contains(text(),"系列名")]/../td/span[1]/a/text()'
|
||||
expr_label2 = '//th[contains(text(),"社团名")]/../td/span[1]/a/text()'
|
||||
expr_extrafanart = '//*[@id="work_left"]/div/div/div[1]/div/@data-src'
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.updateCore(core)
|
||||
self.cookies = {'locale': 'zh-cn'}
|
||||
|
||||
if "RJ" in number or "VJ" in number:
|
||||
self.number = number.upper()
|
||||
self.detailurl = 'https://www.dlsite.com/maniax/work/=/product_id/' + self.number + '.html/?locale=zh_CN'
|
||||
htmltree = self.getHtmlTree(self.detailurl)
|
||||
else:
|
||||
self.detailurl = f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie'
|
||||
htmltree = self.getHtmlTree(self.detailurl)
|
||||
search_result = self.getAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
|
||||
if len(search_result) == 0:
|
||||
number = number.replace("THE ANIMATION", "").replace("he Animation", "").replace("t", "").replace("T","")
|
||||
htmltree = self.getHtmlTree(f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie')
|
||||
search_result = self.getAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
|
||||
if len(search_result) == 0:
|
||||
if "～" in number:
|
||||
number = number.replace("～","〜")
|
||||
elif "〜" in number:
|
||||
number = number.replace("〜","～")
|
||||
htmltree = self.getHtmlTree(f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie')
|
||||
search_result = self.getAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
|
||||
if len(search_result) == 0:
|
||||
number = number.replace('上巻', '').replace('下巻', '').replace('前編', '').replace('後編', '')
|
||||
htmltree = self.getHtmlTree(f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie')
|
||||
search_result = self.getAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
|
||||
self.detailurl = search_result[0]
|
||||
htmltree = self.getHtmlTree(self.detailurl)
|
||||
self.number = str(re.findall("\wJ\w+", self.detailurl)).strip(" [']")
|
||||
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def getNum(self, htmltree):
|
||||
return self.number
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
result = super().getTitle(htmltree)
|
||||
result = result[:result.rfind(' | DLsite')]
|
||||
result = result[:result.rfind(' [')]
|
||||
result = result.replace('【HD版】', '')
|
||||
return result
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
total = []
|
||||
result = self.getAll(htmltree, self.expr_outline)
|
||||
for i in result:
|
||||
total.append(i.strip('\r\n'))
|
||||
return str(total).strip(" ['']").replace("', '', '",r'\n').replace("', '",r'\n').strip(", '', '")
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
return super().getRelease(htmltree).replace('年','-').replace('月','-').replace('日','')
|
||||
|
||||
def getCover(self, htmltree):
|
||||
return 'https:' + super().getCover(htmltree).replace('.webp', '.jpg')
|
||||
|
||||
def getTags(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_tags)
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
try:
|
||||
result = []
|
||||
for i in self.getAll(self.expr_extrafanart):
|
||||
result.append("https:" + i)
|
||||
except:
|
||||
result = ''
|
||||
return result
|
||||
152
scrapinglib/fanza.py
Normal file
152
scrapinglib/fanza.py
Normal file
@@ -0,0 +1,152 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
from urllib.parse import urlencode
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Fanza(Parser):
|
||||
source = 'fanza'
|
||||
|
||||
expr_title = '//*[starts-with(@id, "title")]/text()'
|
||||
expr_outline = "//div[@class='mg-b20 lh4']/text()"
|
||||
expr_outline2 = "//div[@class='mg-b20 lh4']//p/text()"
|
||||
expr_runtime = "//td[contains(text(),'収録時間')]/following-sibling::td/text()"
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number
|
||||
self.updateCore(core)
|
||||
|
||||
# fanza allow letter + number + underscore, normalize the input here
|
||||
# @note: I only find the usage of underscore as h_test123456789
|
||||
fanza_search_number = number
|
||||
# AV_Data_Capture.py.getNumber() over format the input, restore the h_ prefix
|
||||
if fanza_search_number.startswith("h-"):
|
||||
fanza_search_number = fanza_search_number.replace("h-", "h_")
|
||||
|
||||
fanza_search_number = re.sub(r"[^0-9a-zA-Z_]", "", fanza_search_number).lower()
|
||||
|
||||
fanza_urls = [
|
||||
"https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=",
|
||||
"https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=",
|
||||
"https://www.dmm.co.jp/digital/anime/-/detail/=/cid=",
|
||||
"https://www.dmm.co.jp/mono/anime/-/detail/=/cid=",
|
||||
"https://www.dmm.co.jp/digital/videoc/-/detail/=/cid=",
|
||||
"https://www.dmm.co.jp/digital/nikkatsu/-/detail/=/cid=",
|
||||
"https://www.dmm.co.jp/rental/-/detail/=/cid=",
|
||||
]
|
||||
|
||||
for url in fanza_urls:
|
||||
self.detailurl = url + fanza_search_number
|
||||
url = "https://www.dmm.co.jp/age_check/=/declared=yes/?"+ urlencode({"rurl": self.detailurl})
|
||||
self.htmlcode = self.getHtml(url)
|
||||
if self.htmlcode != 404:
|
||||
self.htmltree = etree.HTML(self.htmlcode)
|
||||
break
|
||||
if self.htmlcode == 404:
|
||||
return 404
|
||||
result = self.dictformat(self.htmltree)
|
||||
return result
|
||||
|
||||
def getNum(self, htmltree):
|
||||
# for some old page, the input number does not match the page
|
||||
# for example, the url will be cid=test012
|
||||
# but the hinban on the page is test00012
|
||||
# so get the hinban first, and then pass it to following functions
|
||||
self.fanza_hinban = self.getFanzaString('品番：')
|
||||
self.number = self.fanza_hinban
|
||||
number_lo = self.number.lower()
|
||||
if (re.sub('-|_', '', number_lo) == self.fanza_hinban or
|
||||
number_lo.replace('-', '00') == self.fanza_hinban or
|
||||
number_lo.replace('-', '') + 'so' == self.fanza_hinban
|
||||
):
|
||||
self.number = self.number
|
||||
return self.number
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
return self.getFanzaString('メーカー')
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
try:
|
||||
result = self.getTreeIndex(htmltree, self.expr_outline).replace("\n", "")
|
||||
if result == '':
|
||||
result = self.getTreeIndex(htmltree, self.expr_outline2).replace("\n", "")
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getRuntime(self, htmltree):
|
||||
return str(re.search(r'\d+', super().getRuntime(htmltree)).group()).strip(" ['']")
|
||||
|
||||
def getDirector(self, htmltree):
|
||||
if "anime" not in self.detailurl:
|
||||
return self.getFanzaString('監督：')
|
||||
return ''
|
||||
|
||||
def getActors(self, htmltree):
|
||||
if "anime" not in self.detailurl:
|
||||
return super().getActors(htmltree).replace("', '", ",")
|
||||
return ''
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
result = self.getFanzaString('発売日：')
|
||||
if result == '' or result == '----':
|
||||
result = self.getFanzaString('配信開始日：')
|
||||
return result.replace("/", "-").strip('\\n')
|
||||
|
||||
def getCover(self, htmltree):
|
||||
# return super().getCover(htmltree)
|
||||
cover_number = self.fanza_hinban
|
||||
try:
|
||||
result = self.getTreeIndex(htmltree, '//*[@id="' + cover_number + '"]/@href')
|
||||
except:
|
||||
# sometimes fanza modify _ to \u0005f for image id
|
||||
if "_" in cover_number:
|
||||
cover_number = cover_number.replace("_", r"\u005f")
|
||||
try:
|
||||
result = self.getTreeIndex(htmltree, '//*[@id="' + cover_number + '"]/@href')
|
||||
except:
|
||||
# (TODO) handle more edge case
|
||||
# print(html)
|
||||
# raise exception here, same behavior as before
|
||||
# people's major requirement is fetching the picture
|
||||
raise ValueError("can not find image")
|
||||
return result
|
||||
|
||||
def getTags(self, htmltree):
|
||||
return self.getFanzaStrings('ジャンル：')
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
html_pather = re.compile(r'<div id=\"sample-image-block\"[\s\S]*?<br></div>\n</div>')
|
||||
html = html_pather.search(self.htmlcode)
|
||||
if html:
|
||||
html = html.group()
|
||||
extrafanart_pather = re.compile(r'<img.*?src=\"(.*?)\"')
|
||||
extrafanart_imgs = extrafanart_pather.findall(html)
|
||||
if extrafanart_imgs:
|
||||
s = []
|
||||
for img_url in extrafanart_imgs:
|
||||
img_urls = img_url.rsplit('-', 1)
|
||||
img_url = img_urls[0] + 'jp-' + img_urls[1]
|
||||
s.append(img_url)
|
||||
return s
|
||||
return ''
|
||||
|
||||
def getLabel(self, htmltree):
|
||||
return self.getFanzaStrings('レーベル')
|
||||
|
||||
def getSeries(self, htmltree):
|
||||
return self.getFanzaStrings('シリーズ：')
|
||||
|
||||
def getFanzaString(self, expr):
|
||||
result1 = str(self.htmltree.xpath("//td[contains(text(),'"+expr+"')]/following-sibling::td/a/text()")).strip(" ['']")
|
||||
result2 = str(self.htmltree.xpath("//td[contains(text(),'"+expr+"')]/following-sibling::td/text()")).strip(" ['']")
|
||||
return result1+result2
|
||||
|
||||
def getFanzaStrings(self, string):
|
||||
result1 = self.htmltree.xpath("//td[contains(text(),'" + string + "')]/following-sibling::td/a/text()")
|
||||
if len(result1) > 0:
|
||||
return result1
|
||||
result2 = self.htmltree.xpath("//td[contains(text(),'" + string + "')]/following-sibling::td/text()")
|
||||
return result2
|
||||
73
scrapinglib/fc2.py
Normal file
73
scrapinglib/fc2.py
Normal file
@@ -0,0 +1,73 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
from urllib.parse import urljoin
|
||||
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Fc2(Parser):
|
||||
source = 'fc2'
|
||||
imagecut = 0
|
||||
|
||||
expr_title = '/html/head/title/text()'
|
||||
expr_studio = '//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()'
|
||||
expr_release = '//*[@id="top"]/div[1]/section[1]/div/section/div[2]/div[2]/p/text()'
|
||||
expr_runtime = "//p[@class='items_article_info']/text()"
|
||||
expr_director = '//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()'
|
||||
expr_actor = '//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()'
|
||||
expr_cover = "//div[@class='items_article_MainitemThumb']/span/img/@src"
|
||||
expr_tags = "//a[@class='tag tagTag']/text()"
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number.replace('FC2-', '').replace('fc2-', '')
|
||||
self.updateCore(core)
|
||||
|
||||
self.detailurl = 'https://adult.contents.fc2.com/article/' + self.number + '/'
|
||||
self.htmlcode = self.getHtml(self.detailurl)
|
||||
if self.htmlcode == 404:
|
||||
return 404
|
||||
htmltree = etree.HTML(self.htmlcode)
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def getNum(self, htmltree):
|
||||
return 'FC2-' + self.number
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
return super().getRelease(htmltree).strip(" ['販売日 : ']").replace('/','-')
|
||||
|
||||
def getActors(self, htmltree):
|
||||
actors = super().getActors(htmltree)
|
||||
if not actors:
|
||||
actors = '素人'
|
||||
return actors
|
||||
|
||||
def getCover(self, htmltree):
|
||||
return urljoin('https://adult.contents.fc2.com', super().getCover(htmltree))
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
html_pather = re.compile(r'<ul class=\"items_article_SampleImagesArea\"[\s\S]*?</ul>')
|
||||
html = html_pather.search(self.htmlcode)
|
||||
if html:
|
||||
html = html.group()
|
||||
extrafanart_pather = re.compile(r'<a href=\"(.*?)\"')
|
||||
extrafanart_imgs = extrafanart_pather.findall(html)
|
||||
if extrafanart_imgs:
|
||||
return extrafanart_imgs
|
||||
return ''
|
||||
|
||||
def getTrailer(self, htmltree):
|
||||
video_pather = re.compile(r'\'[a-zA-Z0-9]{32}\'')
|
||||
video = video_pather.findall(self.htmlcode)
|
||||
if video:
|
||||
try:
|
||||
video_url = video[0].replace('\'', '')
|
||||
video_url = 'https://adult.contents.fc2.com/api/v2/videos/' + self.number + '/sample?key=' + video_url
|
||||
url_json = eval(self.getHtml(video_url))['path'].replace('\\', '')
|
||||
return url_json
|
||||
except:
|
||||
return ''
|
||||
else:
|
||||
return ''
|
||||
75
scrapinglib/gcolle.py
Normal file
75
scrapinglib/gcolle.py
Normal file
@@ -0,0 +1,75 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
from .httprequest import get_html_session
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Gcolle(Parser):
|
||||
source = 'gcolle'
|
||||
imagecut = 4
|
||||
|
||||
expr_r18 = '//*[@id="main_content"]/table[1]/tbody/tr/td[2]/table/tbody/tr/td/h4/a[2]/@href'
|
||||
expr_number = '//td[contains(text(),"商品番号")]/../td[2]/text()'
|
||||
expr_title = '//*[@id="cart_quantity"]/table/tr[1]/td/h1/text()'
|
||||
expr_studio = '//td[contains(text(),"アップロード会員名")]/b/text()'
|
||||
expr_director = '//td[contains(text(),"アップロード会員名")]/b/text()'
|
||||
expr_actor = '//td[contains(text(),"アップロード会員名")]/b/text()'
|
||||
expr_label = '//td[contains(text(),"アップロード会員名")]/b/text()'
|
||||
expr_series = '//td[contains(text(),"アップロード会員名")]/b/text()'
|
||||
expr_release = '//td[contains(text(),"商品登録日")]/../td[2]/time/@datetime'
|
||||
expr_cover = '//*[@id="cart_quantity"]/table/tr[3]/td/table/tr/td/a/@href'
|
||||
expr_tags = '//*[@id="cart_quantity"]/table/tr[4]/td/a/text()'
|
||||
expr_outline = '//*[@id="cart_quantity"]/table/tr[3]/td/p/text()'
|
||||
expr_extrafanart = '//*[@id="cart_quantity"]/table/tr[3]/td/div/img/@src'
|
||||
expr_extrafanart2 = '//*[@id="cart_quantity"]/table/tr[3]/td/div/a/img/@src'
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number.upper().replace('GCOLLE-','')
|
||||
self.updateCore(core)
|
||||
|
||||
self.detailurl = 'https://gcolle.net/product_info.php/products_id/' + self.number
|
||||
session = get_html_session(cookies=self.cookies, proxies=self.proxies, verify=self.verify)
|
||||
htmlcode = session.get('https://gcolle.net/product_info.php/products_id/' + number).text
|
||||
htmltree = etree.HTML(htmlcode)
|
||||
|
||||
r18url = self.getTreeIndex(htmltree, self.expr_r18)
|
||||
if r18url and r18url.startswith('http'):
|
||||
htmlcode = session.get(r18url).text
|
||||
htmltree = etree.HTML(htmlcode)
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def getNum(self, htmltree):
|
||||
num = super().getNum(htmltree)
|
||||
if self.number != num:
|
||||
raise Exception(f'[!] {self.number}: find [{num}] in gcolle, not match')
|
||||
return "GCOLLE-" + str(num)
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
result = self.getAll(htmltree, self.expr_outline)
|
||||
try:
|
||||
return "\n".join(result)
|
||||
except:
|
||||
return ""
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
return re.findall('\d{4}-\d{2}-\d{2}', super().getRelease(htmltree))[0]
|
||||
|
||||
def getCover(self, htmltree):
|
||||
return "https:" + super().getCover(htmltree)
|
||||
|
||||
def getTags(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_tags)
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
extrafanart = self.getAll(htmltree, self.expr_extrafanart)
|
||||
if len(extrafanart) == 0:
|
||||
extrafanart = self.getAll(htmltree, self.expr_extrafanart2)
|
||||
# Add "https:" in each extrafanart url
|
||||
for i in range(len(extrafanart)):
|
||||
extrafanart[i] = 'https:' + extrafanart[i]
|
||||
return extrafanart
|
||||
|
||||
|
||||
8
scrapinglib/getchu.py
Normal file
8
scrapinglib/getchu.py
Normal file
@@ -0,0 +1,8 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Getchu(Parser):
|
||||
source = 'getchu'
|
||||
251
scrapinglib/httprequest.py
Normal file
251
scrapinglib/httprequest.py
Normal file
@@ -0,0 +1,251 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import mechanicalsoup
|
||||
import requests
|
||||
from requests.adapters import HTTPAdapter
|
||||
from urllib3.util.retry import Retry
|
||||
from cloudscraper import create_scraper
|
||||
|
||||
G_USER_AGENT = r'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.133 Safari/537.36'
|
||||
G_DEFAULT_TIMEOUT = 10
|
||||
|
||||
def get(url: str, cookies = None, ua: str = None, return_type: str = None, encoding: str = None,
|
||||
retry: int = 3, timeout: int = G_DEFAULT_TIMEOUT, proxies=None, verify=None):
|
||||
"""
|
||||
网页请求核心函数
|
||||
|
||||
是否使用代理应由上层处理
|
||||
"""
|
||||
errors = ""
|
||||
headers = {"User-Agent": ua or G_USER_AGENT}
|
||||
|
||||
for i in range(retry):
|
||||
try:
|
||||
result = requests.get(url, headers=headers, timeout=timeout, proxies=proxies,
|
||||
verify=verify,
|
||||
cookies=cookies)
|
||||
if return_type == "object":
|
||||
return result
|
||||
elif return_type == "content":
|
||||
return result.content
|
||||
else:
|
||||
result.encoding = encoding or result.apparent_encoding
|
||||
return result.text
|
||||
except Exception as e:
|
||||
print(f"[-]Connect: {url} retry {i + 1}/{retry}")
|
||||
errors = str(e)
|
||||
if "getaddrinfo failed" in errors:
|
||||
print("[-]Connect Failed! Please Check your proxy config")
|
||||
print("[-]" + errors)
|
||||
else:
|
||||
print("[-]" + errors)
|
||||
print('[-]Connect Failed! Please check your Proxy or Network!')
|
||||
raise Exception('Connect Failed')
|
||||
|
||||
|
||||
def post(url: str, data: dict, cookies = None, ua: str = None, return_type: str = None, encoding: str = None,
|
||||
retry: int = 3, timeout: int = G_DEFAULT_TIMEOUT, proxies=None, verify=None):
|
||||
"""
|
||||
是否使用代理应由上层处理
|
||||
"""
|
||||
errors = ""
|
||||
headers = {"User-Agent": ua or G_USER_AGENT}
|
||||
|
||||
for i in range(retry):
|
||||
try:
|
||||
result = requests.post(url, data=data, headers=headers, timeout=timeout, proxies=proxies,
|
||||
verify=verify,
|
||||
cookies=cookies)
|
||||
if return_type == "object":
|
||||
return result
|
||||
elif return_type == "content":
|
||||
return result.content
|
||||
else:
|
||||
result.encoding = encoding or result.apparent_encoding
|
||||
return result
|
||||
except Exception as e:
|
||||
print(f"[-]Connect: {url} retry {i + 1}/{retry}")
|
||||
errors = str(e)
|
||||
if "getaddrinfo failed" in errors:
|
||||
print("[-]Connect Failed! Please Check your proxy config")
|
||||
print("[-]" + errors)
|
||||
else:
|
||||
print("[-]" + errors)
|
||||
print('[-]Connect Failed! Please check your Proxy or Network!')
|
||||
raise Exception('Connect Failed')
|
||||
|
||||
|
||||
#
|
||||
# TODO: 以下临时使用，更新完各站后，再更新
|
||||
#
|
||||
|
||||
|
||||
class TimeoutHTTPAdapter(HTTPAdapter):
|
||||
def __init__(self, *args, **kwargs):
|
||||
self.timeout = G_DEFAULT_TIMEOUT
|
||||
if "timeout" in kwargs:
|
||||
self.timeout = kwargs["timeout"]
|
||||
del kwargs["timeout"]
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
def send(self, request, **kwargs):
|
||||
timeout = kwargs.get("timeout")
|
||||
if timeout is None:
|
||||
kwargs["timeout"] = self.timeout
|
||||
return super().send(request, **kwargs)
|
||||
|
||||
|
||||
# with keep-alive feature
|
||||
# storyline carib gcolle javdb only
|
||||
def get_html_session(url: str = None, cookies = None, ua: str = None, return_type: str = None,
|
||||
encoding: str = None, retry: int = 3, timeout: int = G_DEFAULT_TIMEOUT, proxies=None, verify=None):
|
||||
session = requests.Session()
|
||||
retries = Retry(total=retry, connect=retry, backoff_factor=1,
|
||||
status_forcelist=[429, 500, 502, 503, 504])
|
||||
session.mount("https://", TimeoutHTTPAdapter(max_retries=retries, timeout=timeout))
|
||||
session.mount("http://", TimeoutHTTPAdapter(max_retries=retries, timeout=timeout))
|
||||
if isinstance(cookies, dict) and len(cookies):
|
||||
requests.utils.add_dict_to_cookiejar(session.cookies, cookies)
|
||||
if verify:
|
||||
session.verify = verify
|
||||
if proxies:
|
||||
session.proxies = proxies
|
||||
session.headers = {"User-Agent": ua or G_USER_AGENT}
|
||||
try:
|
||||
if isinstance(url, str) and len(url):
|
||||
result = session.get(str(url))
|
||||
else: # 空url参数直接返回可重用session对象，无需设置return_type
|
||||
return session
|
||||
if not result.ok:
|
||||
return None
|
||||
if return_type == "object":
|
||||
return result
|
||||
elif return_type == "content":
|
||||
return result.content
|
||||
elif return_type == "session":
|
||||
return result, session
|
||||
else:
|
||||
result.encoding = encoding or "utf-8"
|
||||
return result.text
|
||||
except requests.exceptions.ProxyError:
|
||||
print("[-]get_html_session() Proxy error! Please check your Proxy")
|
||||
except Exception as e:
|
||||
print(f"[-]get_html_session() failed. {e}")
|
||||
return None
|
||||
|
||||
# storyline only
|
||||
# 使用 cloudscraper....
|
||||
def get_html_by_browser(url: str = None, cookies: dict = None, ua: str = None, return_type: str = None,
|
||||
encoding: str = None, use_scraper: bool = False,
|
||||
retry: int = 3, timeout: int = G_DEFAULT_TIMEOUT, proxies=None, verify=None):
|
||||
session = create_scraper(browser={'custom': ua or G_USER_AGENT, }) if use_scraper else requests.Session()
|
||||
if isinstance(cookies, dict) and len(cookies):
|
||||
requests.utils.add_dict_to_cookiejar(session.cookies, cookies)
|
||||
retries = Retry(total=retry, connect=retry, backoff_factor=1,
|
||||
status_forcelist=[429, 500, 502, 503, 504])
|
||||
session.mount("https://", TimeoutHTTPAdapter(max_retries=retries, timeout=timeout))
|
||||
session.mount("http://", TimeoutHTTPAdapter(max_retries=retries, timeout=timeout))
|
||||
if verify:
|
||||
session.verify = verify
|
||||
if proxies:
|
||||
session.proxies = proxies
|
||||
try:
|
||||
browser = mechanicalsoup.StatefulBrowser(user_agent=ua or G_USER_AGENT, session=session)
|
||||
if isinstance(url, str) and len(url):
|
||||
result = browser.open(url)
|
||||
else:
|
||||
return browser
|
||||
if not result.ok:
|
||||
return None
|
||||
|
||||
if return_type == "object":
|
||||
return result
|
||||
elif return_type == "content":
|
||||
return result.content
|
||||
elif return_type == "browser":
|
||||
return result, browser
|
||||
else:
|
||||
result.encoding = encoding or "utf-8"
|
||||
return result.text
|
||||
except requests.exceptions.ProxyError:
|
||||
print("[-]get_html_by_browser() Proxy error! Please check your Proxy")
|
||||
except Exception as e:
|
||||
print(f'[-]get_html_by_browser() Failed! {e}')
|
||||
return None
|
||||
|
||||
# storyline xcity only
|
||||
def get_html_by_form(url, form_select: str = None, fields: dict = None, cookies: dict = None, ua: str = None,
|
||||
return_type: str = None, encoding: str = None,
|
||||
retry: int = 3, timeout: int = G_DEFAULT_TIMEOUT, proxies=None, verify=None):
|
||||
session = requests.Session()
|
||||
if isinstance(cookies, dict) and len(cookies):
|
||||
requests.utils.add_dict_to_cookiejar(session.cookies, cookies)
|
||||
retries = Retry(total=retry, connect=retry, backoff_factor=1,
|
||||
status_forcelist=[429, 500, 502, 503, 504])
|
||||
session.mount("https://", TimeoutHTTPAdapter(max_retries=retries, timeout=timeout))
|
||||
session.mount("http://", TimeoutHTTPAdapter(max_retries=retries, timeout=timeout))
|
||||
if verify:
|
||||
session.verify = verify
|
||||
if proxies:
|
||||
session.proxies = proxies
|
||||
try:
|
||||
browser = mechanicalsoup.StatefulBrowser(user_agent=ua or G_USER_AGENT, session=session)
|
||||
result = browser.open(url)
|
||||
if not result.ok:
|
||||
return None
|
||||
form = browser.select_form() if form_select is None else browser.select_form(form_select)
|
||||
if isinstance(fields, dict):
|
||||
for k, v in fields.items():
|
||||
browser[k] = v
|
||||
response = browser.submit_selected()
|
||||
|
||||
if return_type == "object":
|
||||
return response
|
||||
elif return_type == "content":
|
||||
return response.content
|
||||
elif return_type == "browser":
|
||||
return response, browser
|
||||
else:
|
||||
result.encoding = encoding or "utf-8"
|
||||
return response.text
|
||||
except requests.exceptions.ProxyError:
|
||||
print("[-]get_html_by_form() Proxy error! Please check your Proxy")
|
||||
except Exception as e:
|
||||
print(f'[-]get_html_by_form() Failed! {e}')
|
||||
return None
|
||||
|
||||
# storyline javdb only
|
||||
def get_html_by_scraper(url: str = None, cookies: dict = None, ua: str = None, return_type: str = None,
|
||||
encoding: str = None, retry: int = 3, proxies=None, timeout: int = G_DEFAULT_TIMEOUT, verify=None):
|
||||
session = create_scraper(browser={'custom': ua or G_USER_AGENT, })
|
||||
if isinstance(cookies, dict) and len(cookies):
|
||||
requests.utils.add_dict_to_cookiejar(session.cookies, cookies)
|
||||
retries = Retry(total=retry, connect=retry, backoff_factor=1,
|
||||
status_forcelist=[429, 500, 502, 503, 504])
|
||||
session.mount("https://", TimeoutHTTPAdapter(max_retries=retries, timeout=timeout))
|
||||
session.mount("http://", TimeoutHTTPAdapter(max_retries=retries, timeout=timeout))
|
||||
if verify:
|
||||
session.verify = verify
|
||||
if proxies:
|
||||
session.proxies = proxies
|
||||
try:
|
||||
if isinstance(url, str) and len(url):
|
||||
result = session.get(str(url))
|
||||
else: # 空url参数直接返回可重用scraper对象，无需设置return_type
|
||||
return session
|
||||
if not result.ok:
|
||||
return None
|
||||
if return_type == "object":
|
||||
return result
|
||||
elif return_type == "content":
|
||||
return result.content
|
||||
elif return_type == "scraper":
|
||||
return result, session
|
||||
else:
|
||||
result.encoding = encoding or "utf-8"
|
||||
return result.text
|
||||
except requests.exceptions.ProxyError:
|
||||
print("[-]get_html_by_scraper() Proxy error! Please check your Proxy")
|
||||
except Exception as e:
|
||||
print(f"[-]get_html_by_scraper() failed. {e}")
|
||||
return None
|
||||
85
scrapinglib/jav321.py
Normal file
85
scrapinglib/jav321.py
Normal file
@@ -0,0 +1,85 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
|
||||
from scrapinglib import httprequest
|
||||
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Jav321(Parser):
|
||||
source = 'jav321'
|
||||
|
||||
expr_title = "/html/body/div[2]/div[1]/div[1]/div[1]/h3/text()"
|
||||
expr_cover = "/html/body/div[2]/div[2]/div[1]/p/a/img/@src"
|
||||
expr_outline = "/html/body/div[2]/div[1]/div[1]/div[2]/div[3]/div/text()"
|
||||
# NOTE: 统一使用 xpath
|
||||
expr_number = '//b[contains(text(),"品番")]/following-sibling::node()'
|
||||
expr_actor = '//b[contains(text(),"出演者")]/following-sibling::a[starts-with(@href,"/star")]'
|
||||
expr_label = '//b[contains(text(),"メーカー")]/following-sibling::a[starts-with(@href,"/company")]'
|
||||
expr_tags = '//b[contains(text(),"ジャンル")]/following-sibling::a[starts-with(@href,"/genre")]'
|
||||
expr_studio = '//b[contains(text(),"メーカー")]/following-sibling::a[starts-with(@href,"/company")]'
|
||||
expr_release = '//b[contains(text(),"配信開始日")]/following-sibling::node()'
|
||||
expr_runtime = '//b[contains(text(),"収録時間")]/following-sibling::node()'
|
||||
# expr_series = '//b[contains(text(),"シリーズ")]'
|
||||
|
||||
def queryNumberUrl(self, number):
|
||||
return 'https://www.jav321.com/search'
|
||||
|
||||
def getHtmlTree(self, url):
|
||||
resp = httprequest.post(url, data={"sn": self.number}, cookies=self.cookies, proxies=self.proxies, verify=self.verify)
|
||||
if "/video/" in resp.url:
|
||||
self.detailurl = resp.url
|
||||
self.detailhtml = resp.text
|
||||
return etree.fromstring(resp.text, etree.HTMLParser())
|
||||
return None
|
||||
|
||||
def getNum(self, htmltree):
|
||||
return super().getNum(htmltree).split(": ")[1]
|
||||
|
||||
def getTrailer(self, htmltree):
|
||||
videourl_pather = re.compile(r'<source src=\"(.*?)\"')
|
||||
videourl = videourl_pather.findall(self.detailhtml)
|
||||
if videourl:
|
||||
url = videourl[0].replace('awscc3001.r18.com', 'cc3001.dmm.co.jp').replace('cc3001.r18.com', 'cc3001.dmm.co.jp')
|
||||
return url
|
||||
else:
|
||||
return ''
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
html_pather = re.compile(r'<div class=\"col\-md\-3\"><div class=\"col\-xs\-12 col\-md\-12\">[\s\S]*?</script><script async src=\"\/\/adserver\.juicyads\.com/js/jads\.js\">')
|
||||
html = html_pather.search(self.detailhtml)
|
||||
if html:
|
||||
html = html.group()
|
||||
extrafanart_pather = re.compile(r'<img.*?src=\"(.*?)\"')
|
||||
extrafanart_imgs = extrafanart_pather.findall(html)
|
||||
if extrafanart_imgs:
|
||||
return extrafanart_imgs
|
||||
return ''
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
return super().getRelease(htmltree).split(": ")[1]
|
||||
|
||||
def getRuntime(self, htmltree):
|
||||
return super().getRuntime(htmltree).split(": ")[1]
|
||||
|
||||
def parseElement(self, all):
|
||||
if all:
|
||||
ret = []
|
||||
for si in all:
|
||||
ret.append(si.text)
|
||||
return ",".join(ret)
|
||||
return ''
|
||||
|
||||
def getActors(self, htmltree):
|
||||
return self.parseElement(super().getActors(htmltree))
|
||||
|
||||
def getLabel(self, htmltree):
|
||||
return self.parseElement(self.getAll(htmltree, self.expr_label))
|
||||
|
||||
def getTags(self, htmltree):
|
||||
return self.parseElement(self.getAll(htmltree, self.expr_tags))
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
return self.parseElement(self.getAll(htmltree, self.expr_studio))
|
||||
145
scrapinglib/javbus.py
Normal file
145
scrapinglib/javbus.py
Normal file
@@ -0,0 +1,145 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
import os
|
||||
import secrets
|
||||
import inspect
|
||||
from lxml import etree
|
||||
from urllib.parse import urljoin
|
||||
from .parser import Parser
|
||||
|
||||
class Javbus(Parser):
|
||||
|
||||
source = 'javbus'
|
||||
|
||||
expr_number = '/html/head/meta[@name="keywords"]/@content'
|
||||
expr_title = '/html/head/title/text()'
|
||||
expr_studio = '//span[contains(text(),"製作商:")]/../a/text()'
|
||||
expr_studio2 = '//span[contains(text(),"メーカー:")]/../a/text()'
|
||||
expr_director = '//span[contains(text(),"導演:")]/../a/text()'
|
||||
expr_directorJa = '//span[contains(text(),"監督:")]/../a/text()'
|
||||
expr_series = '//span[contains(text(),"系列:")]/../a/text()'
|
||||
expr_series2 = '//span[contains(text(),"シリーズ:")]/../a/text()'
|
||||
expr_label = '//span[contains(text(),"系列:")]/../a/text()'
|
||||
expr_cover = '//a[@class="bigImage"]/@href'
|
||||
expr_release = '/html/body/div[5]/div[1]/div[2]/p[2]/text()'
|
||||
expr_runtime = '/html/body/div[5]/div[1]/div[2]/p[3]/text()'
|
||||
expr_actor = '//div[@class="star-name"]/a'
|
||||
expr_actorphoto = '//div[@class="star-name"]/../a/img'
|
||||
expr_tags = '/html/head/meta[@name="keywords"]/@content'
|
||||
expr_uncensored = '//*[@id="navbar"]/ul[1]/li[@class="active"]/a[contains(@href,"uncensored")]'
|
||||
|
||||
def search(self, number, core: None):
|
||||
|
||||
self.number = number
|
||||
self.updateCore(core)
|
||||
try:
|
||||
url = "https://www." + secrets.choice([
|
||||
'buscdn.fun', 'busdmm.fun', 'busfan.fun', 'busjav.fun',
|
||||
'cdnbus.fun',
|
||||
'dmmbus.fun', 'dmmsee.fun',
|
||||
'fanbus.us',
|
||||
'seedmm.fun',
|
||||
]) + "/"
|
||||
try:
|
||||
self.detailurl = url + number
|
||||
self.htmlcode = self.getHtml(self.detailurl)
|
||||
except:
|
||||
self.detailurl = 'https://www.javbus.com/' + number
|
||||
self.htmlcode = self.getHtml(self.detailurl)
|
||||
if self.htmlcode == 404:
|
||||
return 404
|
||||
htmltree = etree.fromstring(self.htmlcode,etree.HTMLParser())
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
except:
|
||||
self.searchUncensored(number)
|
||||
|
||||
def searchUncensored(self, number):
|
||||
""" 二次搜索无码
|
||||
"""
|
||||
self.imagecut = 0
|
||||
self.uncensored = True
|
||||
|
||||
w_number = number.replace('.', '-')
|
||||
self.detailurl = 'https://www.javbus.red/' + w_number
|
||||
self.htmlcode = self.getHtml(self.detailurl)
|
||||
if self.htmlcode == 404:
|
||||
return 404
|
||||
htmltree = etree.fromstring(self.htmlcode, etree.HTMLParser())
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def getNum(self, htmltree):
|
||||
return super().getNum(htmltree).split(',')[0]
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
title = super().getTitle(htmltree)
|
||||
title = str(re.findall('^.+?\s+(.*) - JavBus$', title)[0]).strip()
|
||||
return title
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
if self.uncensored:
|
||||
return self.getTreeIndex(htmltree, self.expr_studio2)
|
||||
else:
|
||||
return self.getTreeIndex(htmltree, self.expr_studio)
|
||||
|
||||
def getCover(self, htmltree):
|
||||
return urljoin("https://www.javbus.com", super().getCover(htmltree))
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
return super().getRelease(htmltree).strip(" ['']")
|
||||
|
||||
def getRuntime(self, htmltree):
|
||||
return super().getRuntime(htmltree).strip(" ['']分鐘")
|
||||
|
||||
def getActors(self, htmltree):
|
||||
actors = super().getActors(htmltree)
|
||||
b=[]
|
||||
for i in actors:
|
||||
b.append(i.attrib['title'])
|
||||
return b
|
||||
|
||||
def getActorPhoto(self, htmltree):
|
||||
actors = super().getActorPhoto(htmltree)
|
||||
d = {}
|
||||
for i in actors:
|
||||
p = i.attrib['src']
|
||||
if "nowprinting.gif" in p:
|
||||
continue
|
||||
t = i.attrib['title']
|
||||
d[t] = urljoin("https://www.javbus.com", p)
|
||||
return d
|
||||
|
||||
def getDirector(self, htmltree):
|
||||
if self.uncensored:
|
||||
return self.getTreeIndex(htmltree, self.expr_directorJa)
|
||||
else:
|
||||
return self.getTreeIndex(htmltree, self.expr_director)
|
||||
|
||||
def getSeries(self, htmltree):
|
||||
if self.uncensored:
|
||||
return self.getTreeIndex(htmltree, self.expr_series2)
|
||||
else:
|
||||
return self.getTreeIndex(htmltree, self.expr_series)
|
||||
|
||||
def getTags(self, htmltree):
|
||||
tags = super().getTags(htmltree).split(',')
|
||||
return tags[1:]
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
html_pather = re.compile(r'<div id=\"sample-waterfall\">[\s\S]*?</div></a>\s*?</div>')
|
||||
html = html_pather.search(self.htmlcode)
|
||||
if html:
|
||||
html = html.group()
|
||||
extrafanart_pather = re.compile(r'<a class=\"sample-box\" href=\"(.*?)\"')
|
||||
extrafanart_imgs = extrafanart_pather.findall(html)
|
||||
if extrafanart_imgs:
|
||||
return [urljoin('https://www.javbus.com',img) for img in extrafanart_imgs]
|
||||
return ''
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
if any(caller for caller in inspect.stack() if os.path.basename(caller.filename) == 'airav.py'):
|
||||
return '' # 从airav.py过来的调用不计算outline直接返回，避免重复抓取数据拖慢处理速度
|
||||
from .storyline import getStoryline
|
||||
return getStoryline(self.number , uncensored = self.uncensored)
|
||||
229
scrapinglib/javdb.py
Normal file
229
scrapinglib/javdb.py
Normal file
@@ -0,0 +1,229 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
|
||||
import re
|
||||
from urllib.parse import urljoin
|
||||
from lxml import etree
|
||||
from requests import session
|
||||
from .httprequest import get_html_session
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Javdb(Parser):
|
||||
source = 'javdb'
|
||||
|
||||
fixstudio = False
|
||||
|
||||
expr_number = '//strong[contains(text(),"番號")]/../span/text()'
|
||||
expr_number2 = '//strong[contains(text(),"番號")]/../span/a/text()'
|
||||
expr_title = "/html/head/title/text()"
|
||||
expr_runtime = '//strong[contains(text(),"時長")]/../span/text()'
|
||||
expr_runtime2 = '//strong[contains(text(),"時長")]/../span/a/text()'
|
||||
expr_uncensored = '//strong[contains(text(),"類別")]/../span/a[contains(@href,"/tags/uncensored?") or contains(@href,"/tags/western?")]'
|
||||
expr_actor = '//span[@class="value"]/a[contains(@href,"/actors/")]/text()'
|
||||
expr_actor2 = '//span[@class="value"]/a[contains(@href,"/actors/")]/../strong/@class'
|
||||
expr_release = '//strong[contains(text(),"日期")]/../span/text()'
|
||||
expr_studio = '//strong[contains(text(),"片商")]/../span/a/text()'
|
||||
expr_studio2 = '//strong[contains(text(),"賣家:")]/../span/a/text()'
|
||||
expr_director = '//strong[contains(text(),"導演")]/../span/text()'
|
||||
expr_director2 = '//strong[contains(text(),"導演")]/../span/a/text()'
|
||||
expr_cover = "//div[contains(@class, 'column-video-cover')]/a/img/@src"
|
||||
expr_cover2 = "//div[contains(@class, 'column-video-cover')]/img/@src"
|
||||
expr_extrafanart = "//article[@class='message video-panel']/div[@class='message-body']/div[@class='tile-images preview-images']/a[contains(@href,'/samples/')]/@href"
|
||||
expr_tags = '//strong[contains(text(),"類別")]/../span/a/text()'
|
||||
expr_tags2 = '//strong[contains(text(),"類別")]/../span/text()'
|
||||
expr_series = '//strong[contains(text(),"系列")]/../span/text()'
|
||||
expr_series2 = '//strong[contains(text(),"系列")]/../span/a/text()'
|
||||
expr_label = '//strong[contains(text(),"系列")]/../span/text()'
|
||||
expr_label2 = '//strong[contains(text(),"系列")]/../span/a/text()'
|
||||
expr_userrating = '//span[@class="score-stars"]/../text()'
|
||||
expr_uservotes = '//span[@class="score-stars"]/../text()'
|
||||
expr_actorphoto = '//strong[contains(text(),"演員:")]/../span/a[starts-with(@href,"/actors/")]'
|
||||
|
||||
def updateCore(self, core):
|
||||
if core.proxies:
|
||||
self.proxies = core.proxies
|
||||
if core.dbcookies:
|
||||
self.cookies = core.dbcookies
|
||||
else:
|
||||
self.cookies = {'over18':'1', 'theme':'auto', 'locale':'zh'}
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number
|
||||
self.updateCore(core)
|
||||
|
||||
self.session = get_html_session(cookies=self.cookies, proxies=self.proxies, verify=self.verify)
|
||||
self.detailurl = self.queryNumberUrl(number)
|
||||
|
||||
self.deatilpage = self.session.get(self.detailurl).text
|
||||
htmltree = etree.fromstring(self.deatilpage, etree.HTMLParser())
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def queryNumberUrl(self, number):
|
||||
javdb_url = 'https://javdb.com/search?q=' + number + '&f=all'
|
||||
try:
|
||||
resp = self.session.get(javdb_url)
|
||||
except Exception as e:
|
||||
print(e)
|
||||
raise Exception(f'[!] {self.number}: page not fond in javdb')
|
||||
|
||||
htmltree = etree.fromstring(resp.text, etree.HTMLParser())
|
||||
# javdb sometime returns multiple results,
|
||||
# and the first elememt maybe not the one we are looking for
|
||||
# iterate all candidates and find the match one
|
||||
urls = self.getAll(htmltree, '//*[contains(@class,"movie-list")]/div/a/@href')
|
||||
# 记录一下欧美的ids ['Blacked','Blacked']
|
||||
if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number):
|
||||
correct_url = urls[0]
|
||||
else:
|
||||
ids = self.getAll(htmltree, '//*[contains(@class,"movie-list")]/div/a/div[contains(@class, "video-title")]/strong/text()')
|
||||
try:
|
||||
correct_url = urls[ids.index(number)]
|
||||
except:
|
||||
# 为避免获得错误番号，只要精确对应的结果
|
||||
if ids[0].upper() != number:
|
||||
raise ValueError("number not found in javdb")
|
||||
correct_url = urls[0]
|
||||
return urljoin(resp.url, correct_url)
|
||||
|
||||
def getNum(self, htmltree):
|
||||
result1 = str(self.getAll(htmltree, self.expr_number)).strip(" ['']")
|
||||
result2 = str(self.getAll(htmltree, self.expr_number2)).strip(" ['']")
|
||||
dp_number = str(result2 + result1).strip('+')
|
||||
# NOTE 检测匹配与更新 self.number
|
||||
if dp_number.upper() != self.number.upper():
|
||||
raise Exception(f'[!] {self.number}: find [{dp_number}] in javdb, not match')
|
||||
self.number = dp_number
|
||||
return self.number
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
browser_title = super().getTitle(htmltree)
|
||||
title = browser_title[:browser_title.find(' | JavDB')].strip()
|
||||
return title.replace(self.number, '').strip()
|
||||
|
||||
def getRuntime(self, htmltree):
|
||||
result1 = str(self.getAll(htmltree, self.expr_runtime)).strip(" ['']")
|
||||
result2 = str(self.getAll(htmltree, self.expr_runtime2)).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').rstrip('mi')
|
||||
|
||||
def getDirector(self, htmltree):
|
||||
result1 = str(self.getAll(htmltree, self.expr_director)).strip(" ['']")
|
||||
result2 = str(self.getAll(htmltree, self.expr_director2)).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
|
||||
def getSeries(self, htmltree):
|
||||
result1 = str(self.getAll(htmltree, self.expr_series)).strip(" ['']")
|
||||
result2 = str(self.getAll(htmltree, self.expr_series2)).strip(" ['']")
|
||||
result = str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
if not result and self.fixstudio:
|
||||
result = self.getStudio(htmltree)
|
||||
return result
|
||||
|
||||
def getLabel(self, htmltree):
|
||||
result1 = str(self.getAll(htmltree, self.expr_label)).strip(" ['']")
|
||||
result2 = str(self.getAll(htmltree, self.expr_label2)).strip(" ['']")
|
||||
result = str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
if not result and self.fixstudio:
|
||||
result = self.getStudio(htmltree)
|
||||
return result
|
||||
|
||||
def getActors(self, htmltree):
|
||||
actors = self.getAll(htmltree, self.expr_actor)
|
||||
genders = self.getAll(htmltree, self.expr_actor2)
|
||||
r = []
|
||||
idx = 0
|
||||
# NOTE only female, we dont care others
|
||||
actor_gendor = 'female'
|
||||
for act in actors:
|
||||
if((actor_gendor == 'all')
|
||||
or (actor_gendor == 'both' and genders[idx] in ['symbol female', 'symbol male'])
|
||||
or (actor_gendor == 'female' and genders[idx] == 'symbol female')
|
||||
or (actor_gendor == 'male' and genders[idx] == 'symbol male')):
|
||||
r.append(act)
|
||||
idx = idx + 1
|
||||
if re.match(r'FC2-[\d]+', self.number, re.A) and not r:
|
||||
r = '素人'
|
||||
self.fixstudio = True
|
||||
return r
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
from .storyline import getStoryline
|
||||
return getStoryline(self.number, self.getUncensored(htmltree))
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
try:
|
||||
return self.getAll(htmltree, self.expr_studio).strip(" ['']")
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
return self.getAll(htmltree, self.expr_studio2).strip(" ['']")
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getTrailer(self, htmltree):
|
||||
video_pather = re.compile(r'<video id\=\".*?>\s*?<source src=\"(.*?)\"')
|
||||
video = video_pather.findall(self.deatilpage)
|
||||
# 加上数组判空
|
||||
if video and video[0] != "":
|
||||
if not 'https:' in video[0]:
|
||||
video_url = 'https:' + video[0]
|
||||
else:
|
||||
video_url = video[0]
|
||||
else:
|
||||
video_url = ''
|
||||
return video_url
|
||||
|
||||
def getTags(self, htmltree):
|
||||
try:
|
||||
return self.getAll(htmltree, self.expr_tags)
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
return self.getAll(htmltree, self.expr_tags2)
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getUserRating(self, htmltree):
|
||||
try:
|
||||
result = str(self.getTreeIndex(htmltree, self.expr_userrating))
|
||||
v = re.findall(r'(\d+|\d+\.\d+)分, 由(\d+)人評價', result)
|
||||
return float(v[0][0])
|
||||
except:
|
||||
return
|
||||
|
||||
def getUserVotes(self, htmltree):
|
||||
try:
|
||||
result = str(self.getTreeIndex(htmltree, self.expr_uservotes))
|
||||
v = re.findall(r'(\d+|\d+\.\d+)分, 由(\d+)人評價', result)
|
||||
return int(v[0][1])
|
||||
except:
|
||||
return
|
||||
|
||||
def getaphoto(self, url, session):
|
||||
html_page = session.get(url).text
|
||||
img_url = re.findall(r'<span class\=\"avatar\" style\=\"background\-image\: url\((.*?)\)', html_page)
|
||||
return img_url[0] if img_url else ''
|
||||
|
||||
def getActorPhoto(self, htmltree):
|
||||
actorall = self.getAll(htmltree, self.expr_actorphoto)
|
||||
if not actorall:
|
||||
return {}
|
||||
actors = self.getActors(htmltree)
|
||||
actor_photo = {}
|
||||
for i in actorall:
|
||||
x = re.findall(r'/actors/(.*)', i.attrib['href'], re.A)
|
||||
if not len(x) or not len(x[0]) or i.text not in actors:
|
||||
continue
|
||||
# NOTE: https://c1.jdbstatic.com 会经常变动，直接使用页面内的地址获取
|
||||
# actor_id = x[0]
|
||||
# pic_url = f"https://c1.jdbstatic.com/avatars/{actor_id[:2].lower()}/{actor_id}.jpg"
|
||||
# if not self.session.head(pic_url).ok:
|
||||
try:
|
||||
pic_url = self.getaphoto(urljoin('https://javdb.com', i.attrib['href']), self.session)
|
||||
if len(pic_url):
|
||||
actor_photo[i.text] = pic_url
|
||||
except:
|
||||
pass
|
||||
return actor_photo
|
||||
|
||||
65
scrapinglib/madou.py
Normal file
65
scrapinglib/madou.py
Normal file
@@ -0,0 +1,65 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
from urllib.parse import urlparse, unquote
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Madou(Parser):
|
||||
source = 'madou'
|
||||
uncensored = True
|
||||
|
||||
expr_url = '//a[@class="share-weixin"]/@data-url'
|
||||
expr_title = "/html/head/title/text()"
|
||||
expr_studio = '//a[@rel="category tag"]/text()'
|
||||
expr_tags = '/html/head/meta[@name="keywords"]/@content'
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number.lower().strip()
|
||||
self.updateCore(core)
|
||||
|
||||
self.detailurl = "https://madou.club/" + number + ".html"
|
||||
self.htmlcode = self.getHtml(self.detailurl)
|
||||
if self.htmlcode == 404:
|
||||
return 404
|
||||
htmltree = etree.fromstring(self.htmlcode, etree.HTMLParser())
|
||||
self.detailurl = self.getTreeIndex(htmltree, self.expr_url)
|
||||
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def getNum(self, htmltree):
|
||||
try:
|
||||
# 解码url
|
||||
filename = unquote(urlparse(self.detailurl).path)
|
||||
# 裁剪文件名
|
||||
result = filename[1:-5].upper().strip()
|
||||
# 移除中文
|
||||
if result.upper() != self.number.upper():
|
||||
result = re.split(r'[^\x00-\x7F]+', result, 1)[0]
|
||||
# 移除多余的符号
|
||||
return result.strip('-')
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
# <title>MD0140-2 / 家有性事EP2 爱在身边-麻豆社</title>
|
||||
# <title>MAD039 机灵可爱小叫花 强诱僧人迫犯色戒-麻豆社</title>
|
||||
# <title>MD0094／贫嘴贱舌中出大嫂／坏嫂嫂和小叔偷腥内射受孕-麻豆社</title>
|
||||
# <title>TM0002-我的痴女女友-麻豆社</title>
|
||||
browser_title = str(super().getTitle(htmltree))
|
||||
title = str(re.findall(r'^[A-Z0-9 /／\-]*(.*)-麻豆社$', browser_title)[0]).strip()
|
||||
return title
|
||||
|
||||
def getCover(self, htmltree):
|
||||
try:
|
||||
url = str(re.findall("shareimage : '(.*?)'", self.htmlcode)[0])
|
||||
return url.strip()
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getTags(self, htmltree):
|
||||
studio = self.getStudio(htmltree)
|
||||
x = super().getTags(htmltree).split(',')
|
||||
return [i.strip() for i in x if len(i.strip()) and studio not in i and '麻豆' not in i]
|
||||
83
scrapinglib/mgstage.py
Normal file
83
scrapinglib/mgstage.py
Normal file
@@ -0,0 +1,83 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
from bs4 import BeautifulSoup
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Mgstage(Parser):
|
||||
source = 'mgstage'
|
||||
|
||||
expr_number = '//th[contains(text(),"品番：")]/../td/a/text()'
|
||||
expr_title = '//*[@id="center_column"]/div[1]/h1/text()'
|
||||
expr_studio = '//th[contains(text(),"メーカー：")]/../td/a/text()'
|
||||
expr_outline = '//p/text()'
|
||||
expr_runtime = '//th[contains(text(),"収録時間：")]/../td/a/text()'
|
||||
expr_director = '//th[contains(text(),"シリーズ")]/../td/a/text()'
|
||||
expr_actor = '//th[contains(text(),"出演：")]/../td/a/text()'
|
||||
expr_release = '//th[contains(text(),"配信開始日：")]/../td/a/text()'
|
||||
expr_cover = '//*[@id="EnlargeImage"]/@href'
|
||||
expr_label = '//th[contains(text(),"シリーズ：")]/../td/a/text()'
|
||||
expr_tags = '//th[contains(text(),"ジャンル：")]/../td/a/text()'
|
||||
expr_tags2 = '//th[contains(text(),"ジャンル：")]/../td/text()'
|
||||
expr_series = '//th[contains(text(),"シリーズ")]/../td/a/text()'
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number.upper()
|
||||
self.updateCore(core)
|
||||
|
||||
self.cookies = {'adc':'1'}
|
||||
self.detailurl = 'https://www.mgstage.com/product/product_detail/'+str(self.number)+'/'
|
||||
self.htmlcode = self.getHtml(self.detailurl)
|
||||
|
||||
soup = BeautifulSoup(self.htmlcode, 'lxml')
|
||||
self.detailpage = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
|
||||
b2 = str(soup.find(attrs={'id': 'introduction'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
|
||||
self.htmlcodetree = etree.HTML(self.htmlcode)
|
||||
self.detailtree = etree.HTML(self.detailpage)
|
||||
self.introtree = etree.HTML(b2)
|
||||
|
||||
result = self.dictformat(self.detailtree)
|
||||
return result
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
return super().getTitle(self.htmlcodetree).replace('/', ',').replace("\\n",'').replace(' ', '').strip()
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
return super().getOutline(self.introtree).strip(" ['']").replace(u'\\n', '').replace("', '', '", '')
|
||||
|
||||
def getCover(self, htmltree):
|
||||
return super().getCover(self.htmlcodetree)
|
||||
|
||||
def getTags(self, htmltree):
|
||||
result1 = str(self.getAll(htmltree, self.expr_tags)).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
result2 = str(self.getAll(htmltree, self.expr_tags2)).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
result = str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','').replace(',,','').split(',')
|
||||
return result
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
html_pather = re.compile(r'<dd>\s*?<ul>[\s\S]*?</ul>\s*?</dd>')
|
||||
html = html_pather.search(self.htmlcode)
|
||||
if html:
|
||||
html = html.group()
|
||||
extrafanart_pather = re.compile(r'<a class=\"sample_image\" href=\"(.*?)\"')
|
||||
extrafanart_imgs = extrafanart_pather.findall(html)
|
||||
if extrafanart_imgs:
|
||||
return extrafanart_imgs
|
||||
return ''
|
||||
|
||||
def getTreeIndex(self, tree, expr, index=0):
|
||||
if expr == '':
|
||||
return ''
|
||||
if tree == self.detailtree:
|
||||
# NOTE: 合并 getMgsString
|
||||
result1 = str(tree.xpath(expr)).strip(" ['']").strip('\\n ').strip('\\n').strip(" ['']").replace(u'\\n', '').replace("', '', '", '')
|
||||
result2 = str(tree.xpath(expr.replace('td/a/','td/'))).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
|
||||
else:
|
||||
result = tree.xpath(expr)
|
||||
try:
|
||||
return result[index]
|
||||
except:
|
||||
return ''
|
||||
93
scrapinglib/mv91.py
Normal file
93
scrapinglib/mv91.py
Normal file
@@ -0,0 +1,93 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Mv91(Parser):
|
||||
source = 'mv91'
|
||||
|
||||
expr_number = '//div[@class="player-title"]/text()'
|
||||
expr_title = '//div[@class="player-title"]/text()'
|
||||
expr_release = '//p[@class="date"]/text()'
|
||||
expr_outline = '//div[@class="play-text"]/text()'
|
||||
expr_tags = '//div[@class="player-tag"]/text()'
|
||||
expr_actor = '//p[@class="player-name"]/text()'
|
||||
|
||||
def getHtmlTree(self, url, type=None):
|
||||
self.htmlcode = self.getHtml(url, type)
|
||||
if self.htmlcode == 404:
|
||||
return 404
|
||||
ret = etree.fromstring(self.htmlcode, etree.HTMLParser())
|
||||
return ret
|
||||
|
||||
def queryNumberUrl(self, number):
|
||||
keyword = number.replace('91CM-','').replace('91MS-','')
|
||||
search_html = self.getHtml('https://www.91mv.org/index/search?keywords=' + keyword)
|
||||
html = etree.fromstring(search_html, etree.HTMLParser())
|
||||
endurl = html.xpath('//a[@class="video-list"]/@href')[0]
|
||||
return 'https://www.91mv.org' + endurl
|
||||
|
||||
def getNum(self, htmltree):
|
||||
try:
|
||||
num = super().getNum(htmltree)
|
||||
finds = re.findall('(.*)(91.*-\d*)',num)
|
||||
if finds:
|
||||
result = str(finds[0][1])
|
||||
else:
|
||||
result = ' '.join(num.replace('/',' ').split())
|
||||
result = result.split()[1]
|
||||
if self.number.upper() != result.upper():
|
||||
raise Exception(f'[!] {self.number}: find {result} in mv91, not match')
|
||||
return result.strip()
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
try:
|
||||
title = super().getTitle(htmltree)
|
||||
finds = re.findall('(.*)(91.*-\d*)',title)
|
||||
if finds:
|
||||
result = str(finds[0][0])
|
||||
else:
|
||||
result = ' '.join(title.replace('/',' ').split())
|
||||
result = result.split()[0].replace('「预告」','')
|
||||
return result.strip()
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
return '91制片厂'
|
||||
|
||||
def getTags(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_tags)
|
||||
|
||||
def getActors(self, htmltree):
|
||||
b=[]
|
||||
for player in self.getAll(htmltree, self.expr_actor):
|
||||
player = player.replace('主演：','')
|
||||
if '/' in player:
|
||||
player = player.split('/')[0]
|
||||
player = re.sub(r'[0-9]+', '', player)
|
||||
b.append(player)
|
||||
return b
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
try:
|
||||
result = super().getRelease(htmltree)
|
||||
date = result.replace('日期：','')
|
||||
if isinstance(date, str) and len(date):
|
||||
return date
|
||||
except:
|
||||
pass
|
||||
return ''
|
||||
|
||||
def getCover(self, htmltree):
|
||||
try:
|
||||
url = str(re.findall('var pic_url = "(.*?)"', self.htmlcode)[0])
|
||||
return url.strip()
|
||||
except:
|
||||
return ''
|
||||
|
||||
259
scrapinglib/parser.py
Normal file
259
scrapinglib/parser.py
Normal file
@@ -0,0 +1,259 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import json
|
||||
import re
|
||||
from lxml import etree, html
|
||||
from . import httprequest
|
||||
|
||||
|
||||
class Parser:
|
||||
|
||||
source = 'base'
|
||||
imagecut = 1
|
||||
uncensored = False
|
||||
# update
|
||||
proxies = None
|
||||
cookies = None
|
||||
verify = None
|
||||
|
||||
number = ''
|
||||
detailurl = ''
|
||||
# xpath expr
|
||||
expr_number = ''
|
||||
expr_title = ''
|
||||
expr_studio = ''
|
||||
expr_studio2 = ''
|
||||
expr_runtime = ''
|
||||
expr_runtime2 = ''
|
||||
expr_release = ''
|
||||
expr_outline = ''
|
||||
expr_director = ''
|
||||
expr_actor = ''
|
||||
expr_tags = ''
|
||||
expr_label = ''
|
||||
expr_label2 = ''
|
||||
expr_series = ''
|
||||
expr_series2 = ''
|
||||
expr_cover = ''
|
||||
expr_cover2 = ''
|
||||
expr_smallcover = ''
|
||||
expr_extrafanart = ''
|
||||
expr_trailer = ''
|
||||
expr_actorphoto = ''
|
||||
expr_uncensored = ''
|
||||
expr_userrating = ''
|
||||
expr_uservotes = ''
|
||||
|
||||
def __init__(self) -> None:
|
||||
pass
|
||||
|
||||
def search(self, number, core: None):
|
||||
""" 搜索番号
|
||||
"""
|
||||
self.number = number
|
||||
self.updateCore(core)
|
||||
|
||||
self.detailurl = self.queryNumberUrl(number)
|
||||
htmltree = self.getHtmlTree(self.detailurl)
|
||||
result = self.dictformat(htmltree)
|
||||
return result
|
||||
|
||||
def updateCore(self, core):
|
||||
""" 从`core`内更新参数
|
||||
|
||||
针对需要传递的参数: cookies, proxy等
|
||||
子类继承后修改
|
||||
"""
|
||||
if core.proxies:
|
||||
self.proxies = core.proxies
|
||||
|
||||
def queryNumberUrl(self, number):
|
||||
""" 根据番号查询详细信息url
|
||||
|
||||
备份查询页面,预览图可能需要
|
||||
"""
|
||||
url = httprequest.get(number)
|
||||
return url
|
||||
|
||||
def getHtml(self, url, type = None):
|
||||
""" 访问网页
|
||||
"""
|
||||
resp = httprequest.get(url, cookies=self.cookies, proxies=self.proxies, verify=self.verify, return_type=type)
|
||||
if '<title>404 Page Not Found' in resp \
|
||||
or '<title>未找到页面' in resp \
|
||||
or '404 Not Found' in resp \
|
||||
or '<title>404' in resp \
|
||||
or '<title>お探しの商品が見つかりません' in resp:
|
||||
return 404
|
||||
return resp
|
||||
|
||||
def getHtmlTree(self, url, type = None):
|
||||
""" 访问网页,返回`etree`
|
||||
"""
|
||||
resp = self.getHtml(url, type)
|
||||
if resp == 404:
|
||||
return 404
|
||||
ret = etree.fromstring(resp, etree.HTMLParser())
|
||||
return ret
|
||||
|
||||
def dictformat(self, htmltree):
|
||||
try:
|
||||
dic = {
|
||||
'number': self.getNum(htmltree),
|
||||
'title': self.getTitle(htmltree),
|
||||
'studio': self.getStudio(htmltree),
|
||||
'year': self.getYear(htmltree),
|
||||
'outline': self.getOutline(htmltree),
|
||||
'runtime': self.getRuntime(htmltree),
|
||||
'director': self.getDirector(htmltree),
|
||||
'actor': self.getActors(htmltree),
|
||||
'release': self.getRelease(htmltree),
|
||||
'cover': self.getCover(htmltree),
|
||||
'cover_small': self.getSmallCover(htmltree),
|
||||
'extrafanart': self.getExtrafanart(htmltree),
|
||||
'trailer': self.getTrailer(htmltree),
|
||||
'imagecut': self.imagecut,
|
||||
'tag': self.getTags(htmltree),
|
||||
'label': self.getLabel(htmltree),
|
||||
'actor_photo': self.getActorPhoto(htmltree),
|
||||
'website': self.detailurl,
|
||||
'source': self.source,
|
||||
'series': self.getSeries(htmltree),
|
||||
'uncensored': self.getUncensored(htmltree),
|
||||
'userrating': self.getUserRating(htmltree),
|
||||
'uservotes': self.getUserVotes(htmltree)
|
||||
}
|
||||
except Exception as e:
|
||||
print(e)
|
||||
dic = {"title": ""}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )
|
||||
return js
|
||||
|
||||
def getNum(self, htmltree):
|
||||
""" 增加 strip 过滤
|
||||
"""
|
||||
return self.getTreeIndex(htmltree, self.expr_number)
|
||||
|
||||
def getTitle(self, htmltree):
|
||||
return self.getTreeIndex(htmltree, self.expr_title).strip()
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_studio).strip(" ['']")
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_studio2).strip(" ['']")
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getYear(self, htmltree):
|
||||
""" year基本都是从release中解析的
|
||||
"""
|
||||
try:
|
||||
release = self.getRelease(htmltree)
|
||||
return str(re.findall('\d{4}', release)).strip(" ['']")
|
||||
except:
|
||||
return release
|
||||
|
||||
def getRuntime(self, htmltree):
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_runtime).strip("\n\t ['']").rstrip('mi')
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_runtime2).strip("\n\t ['']").rstrip('mi')
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
return self.getTreeIndex(htmltree, self.expr_release).strip().replace('/','-')
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
return self.getTreeIndex(htmltree, self.expr_outline).strip().replace("\n","")
|
||||
|
||||
def getDirector(self, htmltree):
|
||||
return self.getTreeIndex(htmltree, self.expr_director)
|
||||
|
||||
def getActors(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_actor)
|
||||
|
||||
def getTags(self, htmltree):
|
||||
return self.getTreeIndex(htmltree, self.expr_tags)
|
||||
|
||||
def getLabel(self, htmltree):
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_label).strip(" ['']")
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_label2).strip(" ['']")
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getSeries(self, htmltree):
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_series).strip(" ['']")
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_series2).strip(" ['']")
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getCover(self, htmltree):
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_cover).strip(" ['']")
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
return self.getTreeIndex(htmltree, self.expr_cover2).strip(" ['']")
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getSmallCover(self, htmltree):
|
||||
return self.getTreeIndex(htmltree, self.expr_smallcover)
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_extrafanart)
|
||||
|
||||
def getTrailer(self, htmltree):
|
||||
return self.getTreeIndex(htmltree, self.expr_trailer)
|
||||
|
||||
def getActorPhoto(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_actorphoto)
|
||||
|
||||
def getUncensored(self, htmlree):
|
||||
if self.expr_uncensored:
|
||||
u = self.getAll(htmlree, self.expr_uncensored)
|
||||
return bool(u)
|
||||
else:
|
||||
return self.uncensored
|
||||
|
||||
def getUserRating(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_userrating)
|
||||
|
||||
def getUserVotes(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_uservotes)
|
||||
|
||||
def getTreeIndex(self, tree: html.HtmlElement, expr, index=0):
|
||||
""" 根据表达式从`xmltree`中获取匹配值,默认 index 为 0
|
||||
"""
|
||||
if expr == '':
|
||||
return ''
|
||||
result = tree.xpath(expr)
|
||||
try:
|
||||
return result[index]
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getAll(self, tree: html.HtmlElement, expr):
|
||||
""" 根据表达式从`xmltree`中获取全部匹配值
|
||||
"""
|
||||
if expr == '':
|
||||
return ''
|
||||
result = tree.xpath(expr)
|
||||
try:
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
291
scrapinglib/storyline.py
Normal file
291
scrapinglib/storyline.py
Normal file
@@ -0,0 +1,291 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
此部分暂未修改
|
||||
|
||||
"""
|
||||
|
||||
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import secrets
|
||||
import builtins
|
||||
from urllib.parse import urljoin
|
||||
from lxml.html import fromstring
|
||||
from multiprocessing.dummy import Pool as ThreadPool
|
||||
from .httprequest import get_html_by_browser, get_html_by_form, get_html_by_scraper, get_html_session
|
||||
|
||||
# 舍弃 Amazon 源
|
||||
G_registered_storyline_site = {"airavwiki", "airav", "avno1", "xcity", "58avgo"}
|
||||
|
||||
G_mode_txt = ('顺序执行','线程池')
|
||||
def is_japanese(raw: str) -> bool:
|
||||
"""
|
||||
日语简单检测
|
||||
"""
|
||||
return bool(re.search(r'[\u3040-\u309F\u30A0-\u30FF\uFF66-\uFF9F]', raw, re.UNICODE))
|
||||
|
||||
class noThread(object):
|
||||
def map(self, fn, param):
|
||||
return list(builtins.map(fn, param))
|
||||
def __enter__(self):
|
||||
return self
|
||||
def __exit__(self, exc_type, exc_val, exc_tb):
|
||||
pass
|
||||
|
||||
|
||||
# 获取剧情介绍 从列表中的站点同时查，取值优先级从前到后
|
||||
def getStoryline(number, title = None, sites: list=None, uncensored=None):
|
||||
start_time = time.time()
|
||||
debug = False
|
||||
storyine_sites = "1:avno1,4:airavwiki".split(',')
|
||||
if uncensored:
|
||||
storyine_sites += "3:58avgo".split(',')
|
||||
else:
|
||||
storyine_sites += "2:airav,5:xcity".split(',')
|
||||
r_dup = set()
|
||||
sort_sites = []
|
||||
for s in storyine_sites:
|
||||
ns = re.sub(r'.*?:', '', s, re.A)
|
||||
if ns in G_registered_storyline_site and ns not in r_dup:
|
||||
sort_sites.append(s)
|
||||
r_dup.add(ns)
|
||||
sort_sites.sort()
|
||||
apply_sites = [re.sub(r'.*?:', '', s, re.A) for s in sort_sites]
|
||||
mp_args = ((site, number, title, debug) for site in apply_sites)
|
||||
cores = min(len(apply_sites), os.cpu_count())
|
||||
if cores == 0:
|
||||
return ''
|
||||
run_mode = 1
|
||||
with ThreadPool(cores) if run_mode > 0 else noThread() as pool:
|
||||
results = pool.map(getStoryline_mp, mp_args)
|
||||
sel = ''
|
||||
|
||||
# 以下debug结果输出会写入日志
|
||||
s = f'[!]Storyline{G_mode_txt[run_mode]}模式运行{len(apply_sites)}个任务共耗时(含启动开销){time.time() - start_time:.3f}秒，结束于{time.strftime("%H:%M:%S")}'
|
||||
sel_site = ''
|
||||
for site, desc in zip(apply_sites, results):
|
||||
if isinstance(desc, str) and len(desc):
|
||||
if not is_japanese(desc):
|
||||
sel_site, sel = site, desc
|
||||
break
|
||||
if not len(sel_site):
|
||||
sel_site, sel = site, desc
|
||||
for site, desc in zip(apply_sites, results):
|
||||
sl = len(desc) if isinstance(desc, str) else 0
|
||||
s += f'，[选中{site}字数:{sl}]' if site == sel_site else f'，{site}字数:{sl}' if sl else f'，{site}:空'
|
||||
print(s)
|
||||
return sel
|
||||
|
||||
|
||||
def getStoryline_mp(args):
|
||||
(site, number, title, debug) = args
|
||||
start_time = time.time()
|
||||
storyline = None
|
||||
if not isinstance(site, str):
|
||||
return storyline
|
||||
elif site == "airavwiki":
|
||||
storyline = getStoryline_airavwiki(number, debug)
|
||||
#storyline = getStoryline_airavwiki_super(number, debug)
|
||||
elif site == "airav":
|
||||
storyline = getStoryline_airav(number, debug)
|
||||
elif site == "avno1":
|
||||
storyline = getStoryline_avno1(number, debug)
|
||||
elif site == "xcity":
|
||||
storyline = getStoryline_xcity(number, debug)
|
||||
# elif site == "amazon":
|
||||
# storyline = getStoryline_amazon(title, number, debug)
|
||||
elif site == "58avgo":
|
||||
storyline = getStoryline_58avgo(number, debug)
|
||||
if not debug:
|
||||
return storyline
|
||||
print("[!]MP 线程[{}]运行{:.3f}秒，结束于{}返回结果: {}".format(
|
||||
site,
|
||||
time.time() - start_time,
|
||||
time.strftime("%H:%M:%S"),
|
||||
storyline if isinstance(storyline, str) and len(storyline) else '[空]')
|
||||
)
|
||||
return storyline
|
||||
|
||||
|
||||
def getStoryline_airav(number, debug):
|
||||
try:
|
||||
site = secrets.choice(('airav.cc','airav4.club'))
|
||||
url = f'https://{site}/searchresults.aspx?Search={number}&Type=0'
|
||||
res, session = get_html_session(url, return_type='session')
|
||||
if not res:
|
||||
raise ValueError(f"get_html_by_session('{url}') failed")
|
||||
lx = fromstring(res.text)
|
||||
urls = lx.xpath('//div[@class="resultcontent"]/ul/li/div/a[@class="ga_click"]/@href')
|
||||
txts = lx.xpath('//div[@class="resultcontent"]/ul/li/div/a[@class="ga_click"]/h3[@class="one_name ga_name"]/text()')
|
||||
detail_url = None
|
||||
for txt, url in zip(txts, urls):
|
||||
if re.search(number, txt, re.I):
|
||||
detail_url = urljoin(res.url, url)
|
||||
break
|
||||
if detail_url is None:
|
||||
raise ValueError("number not found")
|
||||
res = session.get(detail_url)
|
||||
if not res.ok:
|
||||
raise ValueError(f"session.get('{detail_url}') failed")
|
||||
lx = fromstring(res.text)
|
||||
t = str(lx.xpath('/html/head/title/text()')[0]).strip()
|
||||
airav_number = str(re.findall(r'^\s*\[(.*?)]', t)[0])
|
||||
if not re.search(number, airav_number, re.I):
|
||||
raise ValueError(f"page number ->[{airav_number}] not match")
|
||||
desc = str(lx.xpath('//span[@id="ContentPlaceHolder1_Label2"]/text()')[0]).strip()
|
||||
return desc
|
||||
except Exception as e:
|
||||
if debug:
|
||||
print(f"[-]MP getStoryline_airav Error: {e},number [{number}].")
|
||||
pass
|
||||
return None
|
||||
|
||||
|
||||
def getStoryline_airavwiki(number, debug):
|
||||
try:
|
||||
kwd = number[:6] if re.match(r'\d{6}[\-_]\d{2,3}', number) else number
|
||||
url = f'https://cn.airav.wiki/?search={kwd}'
|
||||
result, browser = get_html_by_browser(url, return_type='browser', use_scraper=True)
|
||||
if not result.ok:
|
||||
raise ValueError(f"get_html_by_browser('{url}','{number}') failed")
|
||||
s = browser.page.select('div.row > div > div.videoList.row > div > a.d-block')
|
||||
link = None
|
||||
for a in s:
|
||||
title = a.img['title']
|
||||
list_number = re.findall('^(.*?)\s+', title, re.A)[0].strip()
|
||||
if kwd == number: # 番号PRED-164 和 RED-164需要能够区分
|
||||
if re.match(f'^{number}$', list_number, re.I):
|
||||
link = a
|
||||
break
|
||||
elif re.search(number, list_number, re.I):
|
||||
link = a
|
||||
break
|
||||
if link is None:
|
||||
raise ValueError("number not found")
|
||||
result = browser.follow_link(link)
|
||||
if not result.ok or not re.search(number, browser.url, re.I):
|
||||
raise ValueError("detail page not found")
|
||||
title = browser.page.select('head > title')[0].text.strip()
|
||||
detail_number = str(re.findall('\[(.*?)]', title)[0])
|
||||
if not re.search(number, detail_number, re.I):
|
||||
raise ValueError(f"detail page number not match, got ->[{detail_number}]")
|
||||
desc = browser.page.select_one('div.d-flex.videoDataBlock > div.synopsis > p').text.strip()
|
||||
return desc
|
||||
except Exception as e:
|
||||
if debug:
|
||||
print(f"[-]MP def getStoryline_airavwiki Error: {e}, number [{number}].")
|
||||
pass
|
||||
return ''
|
||||
|
||||
|
||||
def getStoryline_58avgo(number, debug):
|
||||
try:
|
||||
url = 'http://58avgo.com/cn/index.aspx' + secrets.choice([
|
||||
'', '?status=3', '?status=4', '?status=7', '?status=9', '?status=10', '?status=11', '?status=12',
|
||||
'?status=1&Sort=Playon', '?status=1&Sort=dateupload', 'status=1&Sort=dateproduce'
|
||||
]) # 随机选一个，避免网站httpd日志中单个ip的请求太过单一
|
||||
kwd = number[:6] if re.match(r'\d{6}[\-_]\d{2,3}', number) else number
|
||||
result, browser = get_html_by_form(url,
|
||||
fields = {'ctl00$TextBox_SearchKeyWord' : kwd},
|
||||
return_type = 'browser')
|
||||
if not result:
|
||||
raise ValueError(f"get_html_by_form('{url}','{number}') failed")
|
||||
if f'searchresults.aspx?Search={kwd}' not in browser.url:
|
||||
raise ValueError("number not found")
|
||||
s = browser.page.select('div.resultcontent > ul > li.listItem > div.one-info-panel.one > a.ga_click')
|
||||
link = None
|
||||
for a in s:
|
||||
title = a.h3.text.strip()
|
||||
list_number = title[title.rfind(' ')+1:].strip()
|
||||
if re.search(number, list_number, re.I):
|
||||
link = a
|
||||
break
|
||||
if link is None:
|
||||
raise ValueError("number not found")
|
||||
result = browser.follow_link(link)
|
||||
if not result.ok or 'playon.aspx' not in browser.url:
|
||||
raise ValueError("detail page not found")
|
||||
title = browser.page.select_one('head > title').text.strip()
|
||||
detail_number = str(re.findall('\[(.*?)]', title)[0])
|
||||
if not re.search(number, detail_number, re.I):
|
||||
raise ValueError(f"detail page number not match, got ->[{detail_number}]")
|
||||
return browser.page.select_one('#ContentPlaceHolder1_Label2').text.strip()
|
||||
except Exception as e:
|
||||
if debug:
|
||||
print(f"[-]MP getOutline_58avgo Error: {e}, number [{number}].")
|
||||
pass
|
||||
return ''
|
||||
|
||||
|
||||
def getStoryline_avno1(number, debug): #获取剧情介绍 从avno1.cc取得
|
||||
try:
|
||||
site = secrets.choice(['1768av.club','2nine.net','av999.tv','avno1.cc',
|
||||
'hotav.biz','iqq2.xyz','javhq.tv',
|
||||
'www.hdsex.cc','www.porn18.cc','www.xxx18.cc',])
|
||||
url = f'http://{site}/cn/search.php?kw_type=key&kw={number}'
|
||||
lx = fromstring(get_html_by_scraper(url))
|
||||
descs = lx.xpath('//div[@class="type_movie"]/div/ul/li/div/@data-description')
|
||||
titles = lx.xpath('//div[@class="type_movie"]/div/ul/li/div/a/h3/text()')
|
||||
if not descs or not len(descs):
|
||||
raise ValueError(f"number not found")
|
||||
partial_num = bool(re.match(r'\d{6}[\-_]\d{2,3}', number))
|
||||
for title, desc in zip(titles, descs):
|
||||
page_number = title[title.rfind(' ')+1:].strip()
|
||||
if not partial_num:
|
||||
if re.match(f'^{number}$', page_number, re.I):
|
||||
return desc.strip()
|
||||
elif re.search(number, page_number, re.I):
|
||||
return desc.strip()
|
||||
raise ValueError(f"page number ->[{page_number}] not match")
|
||||
except Exception as e:
|
||||
if debug:
|
||||
print(f"[-]MP getOutline_avno1 Error: {e}, number [{number}].")
|
||||
pass
|
||||
return ''
|
||||
|
||||
|
||||
def getStoryline_avno1OLD(number, debug): #获取剧情介绍 从avno1.cc取得
|
||||
try:
|
||||
url = 'http://www.avno1.cc/cn/' + secrets.choice(['usercenter.php?item=' +
|
||||
secrets.choice(['pay_support', 'qa', 'contact', 'guide-vpn']),
|
||||
'?top=1&cat=hd', '?top=1', '?cat=hd', 'porn', '?cat=jp', '?cat=us', 'recommend_category.php'
|
||||
]) # 随机选一个，避免网站httpd日志中单个ip的请求太过单一
|
||||
result, browser = get_html_by_form(url,
|
||||
form_select='div.wrapper > div.header > div.search > form',
|
||||
fields = {'kw' : number},
|
||||
return_type = 'browser')
|
||||
if not result:
|
||||
raise ValueError(f"get_html_by_form('{url}','{number}') failed")
|
||||
s = browser.page.select('div.type_movie > div > ul > li > div')
|
||||
for div in s:
|
||||
title = div.a.h3.text.strip()
|
||||
page_number = title[title.rfind(' ')+1:].strip()
|
||||
if re.search(number, page_number, re.I):
|
||||
return div['data-description'].strip()
|
||||
raise ValueError(f"page number ->[{page_number}] not match")
|
||||
except Exception as e:
|
||||
if debug:
|
||||
print(f"[-]MP getOutline_avno1 Error: {e}, number [{number}].")
|
||||
pass
|
||||
return ''
|
||||
|
||||
|
||||
def getStoryline_xcity(number, debug): #获取剧情介绍 从xcity取得
|
||||
try:
|
||||
xcity_number = number.replace('-','')
|
||||
query_result, browser = get_html_by_form(
|
||||
'https://xcity.jp/' + secrets.choice(['about/','sitemap/','policy/','law/','help/','main/']),
|
||||
fields = {'q' : xcity_number.lower()},
|
||||
return_type = 'browser')
|
||||
if not query_result or not query_result.ok:
|
||||
raise ValueError("page not found")
|
||||
result = browser.follow_link(browser.links('avod\/detail')[0])
|
||||
if not result.ok:
|
||||
raise ValueError("detail page not found")
|
||||
return browser.page.select_one('h2.title-detail + p.lead').text.strip()
|
||||
except Exception as e:
|
||||
if debug:
|
||||
print(f"[-]MP getOutline_xcity Error: {e}, number [{number}].")
|
||||
pass
|
||||
return ''
|
||||
122
scrapinglib/xcity.py
Normal file
122
scrapinglib/xcity.py
Normal file
@@ -0,0 +1,122 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
import secrets
|
||||
from urllib.parse import urljoin
|
||||
from lxml import etree
|
||||
from .httprequest import get_html_by_form
|
||||
from .parser import Parser
|
||||
|
||||
|
||||
class Xcity(Parser):
|
||||
source = 'xcity'
|
||||
|
||||
expr_number = '//*[@id="hinban"]/text()'
|
||||
expr_title = '//*[@id="program_detail_title"]/text()'
|
||||
expr_studio = '//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[1]/li[4]/a/span/text()'
|
||||
expr_studio2 = '//strong[contains(text(),"片商")]/../following-sibling::span/a/text()'
|
||||
expr_runtime = '//span[@class="koumoku" and text()="収録時間"]/../text()'
|
||||
expr_label = '//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[1]/li[5]/a/span/text()'
|
||||
expr_release = '//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[1]/li[2]/text()'
|
||||
expr_tags = '//span[@class="koumoku" and text()="ジャンル"]/../a[starts-with(@href,"/avod/genre/")]/text()'
|
||||
expr_cover = '//*[@id="avodDetails"]/div/div[3]/div[1]/p/a/@href'
|
||||
expr_director = '//*[@id="program_detail_director"]/text()'
|
||||
expr_series = "//span[contains(text(),'シリーズ')]/../a/span/text()"
|
||||
expr_series2 = "//span[contains(text(),'シリーズ')]/../span/text()"
|
||||
|
||||
def getStudio(self, htmltree):
|
||||
return super().getStudio(htmltree).strip('+').replace("', '", '').replace('"', '')
|
||||
|
||||
def getRuntime(self, htmltree):
|
||||
return self.getAll(htmltree, self.expr_runtime)[1].strip()
|
||||
|
||||
def getRelease(self, htmltree):
|
||||
try:
|
||||
result = self.getTreeIndex(htmltree, self.expr_release, 1)
|
||||
return re.findall('\d{4}/\d{2}/\d{2}', result)[0].replace('/','-')
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getTags(self, htmltree):
|
||||
result = self.getAll(htmltree, self.expr_tags)
|
||||
total = []
|
||||
for i in result:
|
||||
total.append(i.replace("\n","").replace("\t",""))
|
||||
return total
|
||||
|
||||
def getCover(self, htmltree):
|
||||
try:
|
||||
result = super().getCover(htmltree)
|
||||
return 'https:' + result
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getDirector(self, htmltree):
|
||||
try:
|
||||
result = super().getDirector(htmltree).replace(u'\n','').replace(u'\t', '')
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getOutline(self, htmltree):
|
||||
from .storyline import getStoryline
|
||||
return getStoryline(self.number, uncensored=False)
|
||||
|
||||
def getActors(self, htmltree):
|
||||
htmla = self.browser.page.select('#avodDetails > div > div.frame > div.content > div > ul.profileCL > li.credit-links > a')
|
||||
t = []
|
||||
for i in htmla:
|
||||
t.append(i.text.strip())
|
||||
return t
|
||||
|
||||
def getActorPhoto(self, htmltree):
|
||||
htmla = self.browser.page.select('#avodDetails > div > div.frame > div.content > div > ul.profileCL > li.credit-links > a')
|
||||
t = {i.text.strip(): i['href'] for i in htmla}
|
||||
o = {}
|
||||
for k, v in t.items():
|
||||
r = self.browser.open_relative(v)
|
||||
if not r.ok:
|
||||
continue
|
||||
pic = self.browser.page.select_one('#avidolDetails > div > div.frame > div > p > img')
|
||||
if 'noimage.gif' in pic['src']:
|
||||
continue
|
||||
o[k] = urljoin(self.browser.url, pic['src'])
|
||||
return o
|
||||
|
||||
def getExtrafanart(self, htmltree):
|
||||
html_pather = re.compile(r'<div id="sample_images".*?>[\s\S]*?</div>')
|
||||
html = html_pather.search(self.detail_page)
|
||||
if html:
|
||||
html = html.group()
|
||||
extrafanart_pather = re.compile(r'<a.*?href=\"(.*?)\"')
|
||||
extrafanart_imgs = extrafanart_pather.findall(html)
|
||||
if extrafanart_imgs:
|
||||
s = []
|
||||
for urli in extrafanart_imgs:
|
||||
urli = 'https:' + urli.replace('/scene/small', '')
|
||||
s.append(urli)
|
||||
return s
|
||||
return ''
|
||||
|
||||
def open_by_browser(self, number):
|
||||
xcity_number = number.replace('-','')
|
||||
query_result, browser = get_html_by_form(
|
||||
'https://xcity.jp/' + secrets.choice(['about/','sitemap/','policy/','law/','help/','main/']),
|
||||
fields = {'q' : xcity_number.lower()},
|
||||
return_type = 'browser')
|
||||
if not query_result or not query_result.ok:
|
||||
raise ValueError("xcity.py: page not found")
|
||||
result = browser.follow_link(browser.links('avod\/detail')[0])
|
||||
if not result.ok:
|
||||
raise ValueError("xcity.py: detail page not found")
|
||||
return str(browser.page), browser
|
||||
|
||||
def search(self, number, core: None):
|
||||
self.number = number
|
||||
self.updateCore(core)
|
||||
|
||||
self.detail_page, self.browser = self.open_by_browser(number)
|
||||
self.detailurl = self.browser.url
|
||||
lx = etree.fromstring(self.detail_page, etree.HTMLParser())
|
||||
result = self.dictformat(lx)
|
||||
return result
|
||||
Reference in New Issue
Block a user