Merge pull request #177 from yoshiko2/revert-168-normalize_EOL
Revert " normalize working tree line endings in Git"
This commit is contained in:
Yoshiko
242
ADC_function.py
242
ADC_function.py
@@ -1,121 +1,121 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import requests
|
||||
from configparser import ConfigParser
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import sys
|
||||
from lxml import etree
|
||||
import sys
|
||||
import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
# sys.setdefaultencoding('utf-8')
|
||||
|
||||
config_file='config.ini'
|
||||
config = ConfigParser()
|
||||
|
||||
if os.path.exists(config_file):
|
||||
try:
|
||||
config.read(config_file, encoding='UTF-8')
|
||||
except:
|
||||
print('[-]Config.ini read failed! Please use the offical file!')
|
||||
else:
|
||||
print('[+]config.ini: not found, creating...',end='')
|
||||
with open("config.ini", "wt", encoding='UTF-8') as code:
|
||||
print("[common]", file=code)
|
||||
print("main_mode = 1", file=code)
|
||||
print("failed_output_folder = failed", file=code)
|
||||
print("success_output_folder = JAV_output", file=code)
|
||||
print("", file=code)
|
||||
print("[proxy]",file=code)
|
||||
print("proxy=127.0.0.1:1081",file=code)
|
||||
print("timeout=10", file=code)
|
||||
print("retry=3", file=code)
|
||||
print("", file=code)
|
||||
print("[Name_Rule]", file=code)
|
||||
print("location_rule=actor+'/'+number",file=code)
|
||||
print("naming_rule=number+'-'+title",file=code)
|
||||
print("", file=code)
|
||||
print("[update]",file=code)
|
||||
print("update_check=1",file=code)
|
||||
print("", file=code)
|
||||
print("[media]", file=code)
|
||||
print("media_warehouse=emby", file=code)
|
||||
print("#emby plex kodi", file=code)
|
||||
print("", file=code)
|
||||
print("[escape]", file=code)
|
||||
print("literals=\\", file=code)
|
||||
print("", file=code)
|
||||
print("[movie_location]", file=code)
|
||||
print("path=", file=code)
|
||||
print("", file=code)
|
||||
print('.',end='')
|
||||
time.sleep(2)
|
||||
print('.')
|
||||
print('[+]config.ini: created!')
|
||||
print('[+]Please restart the program!')
|
||||
time.sleep(4)
|
||||
os._exit(0)
|
||||
try:
|
||||
config.read(config_file, encoding='UTF-8')
|
||||
except:
|
||||
print('[-]Config.ini read failed! Please use the offical file!')
|
||||
|
||||
def get_network_settings():
|
||||
try:
|
||||
proxy = config["proxy"]["proxy"]
|
||||
timeout = int(config["proxy"]["timeout"])
|
||||
retry_count = int(config["proxy"]["retry"])
|
||||
assert timeout > 0
|
||||
assert retry_count > 0
|
||||
except:
|
||||
raise ValueError("[-]Proxy config error! Please check the config.")
|
||||
return proxy, timeout, retry_count
|
||||
|
||||
def getDataState(json_data): # 元数据获取失败检测
|
||||
if json_data['title'] == '' or json_data['title'] == 'None' or json_data['title'] == 'null':
|
||||
return 0
|
||||
else:
|
||||
return 1
|
||||
|
||||
def ReadMediaWarehouse():
|
||||
return config['media']['media_warehouse']
|
||||
|
||||
def UpdateCheckSwitch():
|
||||
check=str(config['update']['update_check'])
|
||||
if check == '1':
|
||||
return '1'
|
||||
elif check == '0':
|
||||
return '0'
|
||||
elif check == '':
|
||||
return '0'
|
||||
|
||||
def getXpathSingle(htmlcode,xpath):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result1 = str(html.xpath(xpath)).strip(" ['']")
|
||||
return result1
|
||||
|
||||
def get_html(url,cookies = None):#网页请求核心
|
||||
proxy, timeout, retry_count = get_network_settings()
|
||||
i = 0
|
||||
while i < retry_count:
|
||||
try:
|
||||
if not proxy == '':
|
||||
proxies = {"http": "http://" + proxy,"https": "https://" + proxy}
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
|
||||
getweb = requests.get(str(url), headers=headers, timeout=timeout,proxies=proxies, cookies=cookies)
|
||||
getweb.encoding = 'utf-8'
|
||||
return getweb.text
|
||||
else:
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
|
||||
getweb = requests.get(str(url), headers=headers, timeout=timeout, cookies=cookies)
|
||||
getweb.encoding = 'utf-8'
|
||||
return getweb.text
|
||||
except:
|
||||
i += 1
|
||||
print('[-]Connect retry '+str(i)+'/'+str(retry_count))
|
||||
print('[-]Connect Failed! Please check your Proxy or Network!')
|
||||
|
||||
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import requests
|
||||
from configparser import ConfigParser
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import sys
|
||||
from lxml import etree
|
||||
import sys
|
||||
import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
# sys.setdefaultencoding('utf-8')
|
||||
|
||||
config_file='config.ini'
|
||||
config = ConfigParser()
|
||||
|
||||
if os.path.exists(config_file):
|
||||
try:
|
||||
config.read(config_file, encoding='UTF-8')
|
||||
except:
|
||||
print('[-]Config.ini read failed! Please use the offical file!')
|
||||
else:
|
||||
print('[+]config.ini: not found, creating...',end='')
|
||||
with open("config.ini", "wt", encoding='UTF-8') as code:
|
||||
print("[common]", file=code)
|
||||
print("main_mode = 1", file=code)
|
||||
print("failed_output_folder = failed", file=code)
|
||||
print("success_output_folder = JAV_output", file=code)
|
||||
print("", file=code)
|
||||
print("[proxy]",file=code)
|
||||
print("proxy=127.0.0.1:1081",file=code)
|
||||
print("timeout=10", file=code)
|
||||
print("retry=3", file=code)
|
||||
print("", file=code)
|
||||
print("[Name_Rule]", file=code)
|
||||
print("location_rule=actor+'/'+number",file=code)
|
||||
print("naming_rule=number+'-'+title",file=code)
|
||||
print("", file=code)
|
||||
print("[update]",file=code)
|
||||
print("update_check=1",file=code)
|
||||
print("", file=code)
|
||||
print("[media]", file=code)
|
||||
print("media_warehouse=emby", file=code)
|
||||
print("#emby plex kodi", file=code)
|
||||
print("", file=code)
|
||||
print("[escape]", file=code)
|
||||
print("literals=\\", file=code)
|
||||
print("", file=code)
|
||||
print("[movie_location]", file=code)
|
||||
print("path=", file=code)
|
||||
print("", file=code)
|
||||
print('.',end='')
|
||||
time.sleep(2)
|
||||
print('.')
|
||||
print('[+]config.ini: created!')
|
||||
print('[+]Please restart the program!')
|
||||
time.sleep(4)
|
||||
os._exit(0)
|
||||
try:
|
||||
config.read(config_file, encoding='UTF-8')
|
||||
except:
|
||||
print('[-]Config.ini read failed! Please use the offical file!')
|
||||
|
||||
def get_network_settings():
|
||||
try:
|
||||
proxy = config["proxy"]["proxy"]
|
||||
timeout = int(config["proxy"]["timeout"])
|
||||
retry_count = int(config["proxy"]["retry"])
|
||||
assert timeout > 0
|
||||
assert retry_count > 0
|
||||
except:
|
||||
raise ValueError("[-]Proxy config error! Please check the config.")
|
||||
return proxy, timeout, retry_count
|
||||
|
||||
def getDataState(json_data): # 元数据获取失败检测
|
||||
if json_data['title'] == '' or json_data['title'] == 'None' or json_data['title'] == 'null':
|
||||
return 0
|
||||
else:
|
||||
return 1
|
||||
|
||||
def ReadMediaWarehouse():
|
||||
return config['media']['media_warehouse']
|
||||
|
||||
def UpdateCheckSwitch():
|
||||
check=str(config['update']['update_check'])
|
||||
if check == '1':
|
||||
return '1'
|
||||
elif check == '0':
|
||||
return '0'
|
||||
elif check == '':
|
||||
return '0'
|
||||
|
||||
def getXpathSingle(htmlcode,xpath):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result1 = str(html.xpath(xpath)).strip(" ['']")
|
||||
return result1
|
||||
|
||||
def get_html(url,cookies = None):#网页请求核心
|
||||
proxy, timeout, retry_count = get_network_settings()
|
||||
i = 0
|
||||
while i < retry_count:
|
||||
try:
|
||||
if not proxy == '':
|
||||
proxies = {"http": "http://" + proxy,"https": "https://" + proxy}
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
|
||||
getweb = requests.get(str(url), headers=headers, timeout=timeout,proxies=proxies, cookies=cookies)
|
||||
getweb.encoding = 'utf-8'
|
||||
return getweb.text
|
||||
else:
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
|
||||
getweb = requests.get(str(url), headers=headers, timeout=timeout, cookies=cookies)
|
||||
getweb.encoding = 'utf-8'
|
||||
return getweb.text
|
||||
except:
|
||||
i += 1
|
||||
print('[-]Connect retry '+str(i)+'/'+str(retry_count))
|
||||
print('[-]Connect Failed! Please check your Proxy or Network!')
|
||||
|
||||
|
||||
|
||||
228
avsox.py
228
avsox.py
@@ -1,115 +1,115 @@
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'avatar-box'})
|
||||
d = {}
|
||||
for i in a:
|
||||
l = i.img['src']
|
||||
t = i.span.get_text()
|
||||
p2 = {t: l}
|
||||
d.update(p2)
|
||||
return d
|
||||
def getTitle(a):
|
||||
try:
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/h3/text()')).strip(" ['']") #[0]
|
||||
return result.replace('/', '')
|
||||
except:
|
||||
return ''
|
||||
def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
soup = BeautifulSoup(a, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'avatar-box'})
|
||||
d = []
|
||||
for i in a:
|
||||
d.append(i.span.get_text())
|
||||
return d
|
||||
def getStudio(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//p[contains(text(),"制作商: ")]/following-sibling::p[1]/a/text()')).strip(" ['']").replace("', '",' ')
|
||||
return result1
|
||||
def getRuntime(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"长度:")]/../text()')).strip(" ['分钟']")
|
||||
return result1
|
||||
def getLabel(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//p[contains(text(),"系列:")]/following-sibling::p[1]/a/text()')).strip(" ['']")
|
||||
return result1
|
||||
def getNum(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"识别码:")]/../span[2]/text()')).strip(" ['']")
|
||||
return result1
|
||||
def getYear(release):
|
||||
try:
|
||||
result = str(re.search('\d{4}',release).group())
|
||||
return result
|
||||
except:
|
||||
return release
|
||||
def getRelease(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"发行时间:")]/../text()')).strip(" ['']")
|
||||
return result1
|
||||
def getCover(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div[1]/div[1]/a/img/@src')).strip(" ['']")
|
||||
return result
|
||||
def getCover_small(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']")
|
||||
return result
|
||||
def getTag(a): # 获取演员
|
||||
soup = BeautifulSoup(a, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'genre'})
|
||||
d = []
|
||||
for i in a:
|
||||
d.append(i.get_text())
|
||||
return d
|
||||
|
||||
def main(number):
|
||||
a = get_html('https://avsox.host/cn/search/' + number)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
if result1 == '' or result1 == 'null' or result1 == 'None':
|
||||
a = get_html('https://avsox.host/cn/search/' + number.replace('-', '_'))
|
||||
print(a)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
if result1 == '' or result1 == 'null' or result1 == 'None':
|
||||
a = get_html('https://avsox.host/cn/search/' + number.replace('_', ''))
|
||||
print(a)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
web = get_html(result1)
|
||||
soup = BeautifulSoup(web, 'lxml')
|
||||
info = str(soup.find(attrs={'class': 'row movie'}))
|
||||
dic = {
|
||||
'actor': getActor(web),
|
||||
'title': getTitle(web).strip(getNum(web)),
|
||||
'studio': getStudio(info),
|
||||
'outline': '',#
|
||||
'runtime': getRuntime(info),
|
||||
'director': '', #
|
||||
'release': getRelease(info),
|
||||
'number': getNum(info),
|
||||
'cover': getCover(web),
|
||||
'cover_small': getCover_small(a),
|
||||
'imagecut': 3,
|
||||
'tag': getTag(web),
|
||||
'label': getLabel(info),
|
||||
'year': getYear(getRelease(info)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': getActorPhoto(web),
|
||||
'website': result1,
|
||||
'source': 'avsox.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'avatar-box'})
|
||||
d = {}
|
||||
for i in a:
|
||||
l = i.img['src']
|
||||
t = i.span.get_text()
|
||||
p2 = {t: l}
|
||||
d.update(p2)
|
||||
return d
|
||||
def getTitle(a):
|
||||
try:
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/h3/text()')).strip(" ['']") #[0]
|
||||
return result.replace('/', '')
|
||||
except:
|
||||
return ''
|
||||
def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
soup = BeautifulSoup(a, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'avatar-box'})
|
||||
d = []
|
||||
for i in a:
|
||||
d.append(i.span.get_text())
|
||||
return d
|
||||
def getStudio(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//p[contains(text(),"制作商: ")]/following-sibling::p[1]/a/text()')).strip(" ['']").replace("', '",' ')
|
||||
return result1
|
||||
def getRuntime(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"长度:")]/../text()')).strip(" ['分钟']")
|
||||
return result1
|
||||
def getLabel(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//p[contains(text(),"系列:")]/following-sibling::p[1]/a/text()')).strip(" ['']")
|
||||
return result1
|
||||
def getNum(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"识别码:")]/../span[2]/text()')).strip(" ['']")
|
||||
return result1
|
||||
def getYear(release):
|
||||
try:
|
||||
result = str(re.search('\d{4}',release).group())
|
||||
return result
|
||||
except:
|
||||
return release
|
||||
def getRelease(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"发行时间:")]/../text()')).strip(" ['']")
|
||||
return result1
|
||||
def getCover(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div[1]/div[1]/a/img/@src')).strip(" ['']")
|
||||
return result
|
||||
def getCover_small(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']")
|
||||
return result
|
||||
def getTag(a): # 获取演员
|
||||
soup = BeautifulSoup(a, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'genre'})
|
||||
d = []
|
||||
for i in a:
|
||||
d.append(i.get_text())
|
||||
return d
|
||||
|
||||
def main(number):
|
||||
a = get_html('https://avsox.host/cn/search/' + number)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
if result1 == '' or result1 == 'null' or result1 == 'None':
|
||||
a = get_html('https://avsox.host/cn/search/' + number.replace('-', '_'))
|
||||
print(a)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
if result1 == '' or result1 == 'null' or result1 == 'None':
|
||||
a = get_html('https://avsox.host/cn/search/' + number.replace('_', ''))
|
||||
print(a)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
web = get_html(result1)
|
||||
soup = BeautifulSoup(web, 'lxml')
|
||||
info = str(soup.find(attrs={'class': 'row movie'}))
|
||||
dic = {
|
||||
'actor': getActor(web),
|
||||
'title': getTitle(web).strip(getNum(web)),
|
||||
'studio': getStudio(info),
|
||||
'outline': '',#
|
||||
'runtime': getRuntime(info),
|
||||
'director': '', #
|
||||
'release': getRelease(info),
|
||||
'number': getNum(info),
|
||||
'cover': getCover(web),
|
||||
'cover_small': getCover_small(a),
|
||||
'imagecut': 3,
|
||||
'tag': getTag(web),
|
||||
'label': getLabel(info),
|
||||
'year': getYear(getRelease(info)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': getActorPhoto(web),
|
||||
'website': result1,
|
||||
'source': 'avsox.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
#print(main('012717_472'))
|
||||
458
fanza.py
458
fanza.py
@@ -1,229 +1,229 @@
|
||||
#!/usr/bin/python3
|
||||
# -*- coding: utf-8 -*-
|
||||
import json
|
||||
import re
|
||||
|
||||
from lxml import etree
|
||||
|
||||
from ADC_function import *
|
||||
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
|
||||
def getTitle(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser())
|
||||
result = html.xpath('//*[@id="title"]/text()')[0]
|
||||
return result
|
||||
|
||||
|
||||
def getActor(text):
|
||||
# //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
html = etree.fromstring(text, etree.HTMLParser())
|
||||
result = (
|
||||
str(
|
||||
html.xpath(
|
||||
"//td[contains(text(),'出演者')]/following-sibling::td/span/a/text()"
|
||||
)
|
||||
)
|
||||
.strip(" ['']")
|
||||
.replace("', '", ",")
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def getStudio(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'メーカー')]/following-sibling::td/a/text()"
|
||||
)[0]
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'メーカー')]/following-sibling::td/text()"
|
||||
)[0]
|
||||
return result
|
||||
|
||||
|
||||
def getRuntime(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result = html.xpath("//td[contains(text(),'収録時間')]/following-sibling::td/text()")[0]
|
||||
return re.search(r"\d+", str(result)).group()
|
||||
|
||||
|
||||
def getLabel(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'シリーズ：')]/following-sibling::td/a/text()"
|
||||
)[0]
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'シリーズ：')]/following-sibling::td/text()"
|
||||
)[0]
|
||||
return result
|
||||
|
||||
|
||||
def getNum(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'品番：')]/following-sibling::td/a/text()"
|
||||
)[0]
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'品番：')]/following-sibling::td/text()"
|
||||
)[0]
|
||||
return result
|
||||
|
||||
|
||||
def getYear(getRelease):
|
||||
try:
|
||||
result = str(re.search(r"\d{4}", getRelease).group())
|
||||
return result
|
||||
except:
|
||||
return getRelease
|
||||
|
||||
|
||||
def getRelease(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'発売日：')]/following-sibling::td/a/text()"
|
||||
)[0].lstrip("\n")
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'発売日：')]/following-sibling::td/text()"
|
||||
)[0].lstrip("\n")
|
||||
return result
|
||||
|
||||
|
||||
def getTag(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'ジャンル：')]/following-sibling::td/a/text()"
|
||||
)
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'ジャンル：')]/following-sibling::td/text()"
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def getCover(text, number):
|
||||
html = etree.fromstring(text, etree.HTMLParser())
|
||||
cover_number = number
|
||||
try:
|
||||
result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0]
|
||||
except:
|
||||
# sometimes fanza modify _ to \u0005f for image id
|
||||
if "_" in cover_number:
|
||||
cover_number = cover_number.replace("_", r"\u005f")
|
||||
try:
|
||||
result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0]
|
||||
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 getDirector(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'監督：')]/following-sibling::td/a/text()"
|
||||
)[0]
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'監督：')]/following-sibling::td/text()"
|
||||
)[0]
|
||||
return result
|
||||
|
||||
|
||||
def getOutline(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser())
|
||||
try:
|
||||
result = str(html.xpath("//div[@class='mg-b20 lh4']/text()")[0]).replace(
|
||||
"\n", ""
|
||||
)
|
||||
if result == "":
|
||||
result = str(html.xpath("//div[@class='mg-b20 lh4']//p/text()")[0]).replace(
|
||||
"\n", ""
|
||||
)
|
||||
except:
|
||||
# (TODO) handle more edge case
|
||||
# print(html)
|
||||
return ""
|
||||
return result
|
||||
|
||||
|
||||
def main(number):
|
||||
# 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=",
|
||||
]
|
||||
chosen_url = ""
|
||||
for url in fanza_urls:
|
||||
chosen_url = url + fanza_search_number
|
||||
htmlcode = get_html(chosen_url)
|
||||
if "404 Not Found" not in htmlcode:
|
||||
break
|
||||
if "404 Not Found" in htmlcode:
|
||||
return json.dumps({"title": "",})
|
||||
try:
|
||||
# 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
|
||||
fanza_hinban = getNum(htmlcode)
|
||||
data = {
|
||||
"title": getTitle(htmlcode).strip(getActor(htmlcode)),
|
||||
"studio": getStudio(htmlcode),
|
||||
"outline": getOutline(htmlcode),
|
||||
"runtime": getRuntime(htmlcode),
|
||||
"director": getDirector(htmlcode) if "anime" not in chosen_url else "",
|
||||
"actor": getActor(htmlcode) if "anime" not in chosen_url else "",
|
||||
"release": getRelease(htmlcode),
|
||||
"number": fanza_hinban,
|
||||
"cover": getCover(htmlcode, fanza_hinban),
|
||||
"imagecut": 1,
|
||||
"tag": getTag(htmlcode),
|
||||
"label": getLabel(htmlcode),
|
||||
"year": getYear(
|
||||
getRelease(htmlcode)
|
||||
), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
"actor_photo": "",
|
||||
"website": chosen_url,
|
||||
"source": "fanza.py",
|
||||
}
|
||||
except:
|
||||
data = {
|
||||
"title": "",
|
||||
}
|
||||
js = json.dumps(
|
||||
data, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ":")
|
||||
) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# print(main("DV-1562"))
|
||||
# input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。")
|
||||
# print(main("ipx292"))
|
||||
pass
|
||||
#!/usr/bin/python3
|
||||
# -*- coding: utf-8 -*-
|
||||
import json
|
||||
import re
|
||||
|
||||
from lxml import etree
|
||||
|
||||
from ADC_function import *
|
||||
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
|
||||
def getTitle(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser())
|
||||
result = html.xpath('//*[@id="title"]/text()')[0]
|
||||
return result
|
||||
|
||||
|
||||
def getActor(text):
|
||||
# //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
html = etree.fromstring(text, etree.HTMLParser())
|
||||
result = (
|
||||
str(
|
||||
html.xpath(
|
||||
"//td[contains(text(),'出演者')]/following-sibling::td/span/a/text()"
|
||||
)
|
||||
)
|
||||
.strip(" ['']")
|
||||
.replace("', '", ",")
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def getStudio(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'メーカー')]/following-sibling::td/a/text()"
|
||||
)[0]
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'メーカー')]/following-sibling::td/text()"
|
||||
)[0]
|
||||
return result
|
||||
|
||||
|
||||
def getRuntime(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result = html.xpath("//td[contains(text(),'収録時間')]/following-sibling::td/text()")[0]
|
||||
return re.search(r"\d+", str(result)).group()
|
||||
|
||||
|
||||
def getLabel(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'シリーズ：')]/following-sibling::td/a/text()"
|
||||
)[0]
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'シリーズ：')]/following-sibling::td/text()"
|
||||
)[0]
|
||||
return result
|
||||
|
||||
|
||||
def getNum(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'品番：')]/following-sibling::td/a/text()"
|
||||
)[0]
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'品番：')]/following-sibling::td/text()"
|
||||
)[0]
|
||||
return result
|
||||
|
||||
|
||||
def getYear(getRelease):
|
||||
try:
|
||||
result = str(re.search(r"\d{4}", getRelease).group())
|
||||
return result
|
||||
except:
|
||||
return getRelease
|
||||
|
||||
|
||||
def getRelease(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'発売日：')]/following-sibling::td/a/text()"
|
||||
)[0].lstrip("\n")
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'発売日：')]/following-sibling::td/text()"
|
||||
)[0].lstrip("\n")
|
||||
return result
|
||||
|
||||
|
||||
def getTag(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'ジャンル：')]/following-sibling::td/a/text()"
|
||||
)
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'ジャンル：')]/following-sibling::td/text()"
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def getCover(text, number):
|
||||
html = etree.fromstring(text, etree.HTMLParser())
|
||||
cover_number = number
|
||||
try:
|
||||
result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0]
|
||||
except:
|
||||
# sometimes fanza modify _ to \u0005f for image id
|
||||
if "_" in cover_number:
|
||||
cover_number = cover_number.replace("_", r"\u005f")
|
||||
try:
|
||||
result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0]
|
||||
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 getDirector(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'監督：')]/following-sibling::td/a/text()"
|
||||
)[0]
|
||||
except:
|
||||
result = html.xpath(
|
||||
"//td[contains(text(),'監督：')]/following-sibling::td/text()"
|
||||
)[0]
|
||||
return result
|
||||
|
||||
|
||||
def getOutline(text):
|
||||
html = etree.fromstring(text, etree.HTMLParser())
|
||||
try:
|
||||
result = str(html.xpath("//div[@class='mg-b20 lh4']/text()")[0]).replace(
|
||||
"\n", ""
|
||||
)
|
||||
if result == "":
|
||||
result = str(html.xpath("//div[@class='mg-b20 lh4']//p/text()")[0]).replace(
|
||||
"\n", ""
|
||||
)
|
||||
except:
|
||||
# (TODO) handle more edge case
|
||||
# print(html)
|
||||
return ""
|
||||
return result
|
||||
|
||||
|
||||
def main(number):
|
||||
# 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=",
|
||||
]
|
||||
chosen_url = ""
|
||||
for url in fanza_urls:
|
||||
chosen_url = url + fanza_search_number
|
||||
htmlcode = get_html(chosen_url)
|
||||
if "404 Not Found" not in htmlcode:
|
||||
break
|
||||
if "404 Not Found" in htmlcode:
|
||||
return json.dumps({"title": "",})
|
||||
try:
|
||||
# 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
|
||||
fanza_hinban = getNum(htmlcode)
|
||||
data = {
|
||||
"title": getTitle(htmlcode).strip(getActor(htmlcode)),
|
||||
"studio": getStudio(htmlcode),
|
||||
"outline": getOutline(htmlcode),
|
||||
"runtime": getRuntime(htmlcode),
|
||||
"director": getDirector(htmlcode) if "anime" not in chosen_url else "",
|
||||
"actor": getActor(htmlcode) if "anime" not in chosen_url else "",
|
||||
"release": getRelease(htmlcode),
|
||||
"number": fanza_hinban,
|
||||
"cover": getCover(htmlcode, fanza_hinban),
|
||||
"imagecut": 1,
|
||||
"tag": getTag(htmlcode),
|
||||
"label": getLabel(htmlcode),
|
||||
"year": getYear(
|
||||
getRelease(htmlcode)
|
||||
), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
"actor_photo": "",
|
||||
"website": chosen_url,
|
||||
"source": "fanza.py",
|
||||
}
|
||||
except:
|
||||
data = {
|
||||
"title": "",
|
||||
}
|
||||
js = json.dumps(
|
||||
data, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ":")
|
||||
) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# print(main("DV-1562"))
|
||||
# input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。")
|
||||
# print(main("ipx292"))
|
||||
pass
|
||||
|
||||
324
fc2fans_club.py
324
fc2fans_club.py
@@ -1,162 +1,162 @@
|
||||
import re
|
||||
from lxml import etree#need install
|
||||
import json
|
||||
import ADC_function
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
def getTitle(htmlcode): #获取厂商
|
||||
#print(htmlcode)
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h3/text()')).strip(" ['']")
|
||||
result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
|
||||
#print(result2)
|
||||
return result2
|
||||
def getActor(htmlcode):
|
||||
try:
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[5]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
def getStudio(htmlcode): #获取厂商
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getNum(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
|
||||
#print(result)
|
||||
return result
|
||||
def getRelease(htmlcode2): #
|
||||
#a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
|
||||
html=etree.fromstring(htmlcode2,etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getCover(htmlcode,number,htmlcode2): #获取厂商 #
|
||||
#a = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id=' + str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") + '&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
|
||||
if result == '':
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']")
|
||||
return 'https://fc2club.com' + result2
|
||||
return 'http:' + result
|
||||
def getOutline(htmlcode2): #获取番号 #
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[1]/div[2]/div[2]/div[1]/div/article/section[4]/p/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
|
||||
return result
|
||||
def getTag(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
|
||||
return result.strip(" ['']").replace("'",'').replace(' ','')
|
||||
def getYear(release):
|
||||
try:
|
||||
result = re.search('\d{4}',release).group()
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getTitle_fc2com(htmlcode): #获取厂商
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/h3/text()')[0]
|
||||
return result
|
||||
def getActor_fc2com(htmlcode):
|
||||
try:
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')[0]
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
def getStudio_fc2com(htmlcode): #获取厂商
|
||||
try:
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
def getNum_fc2com(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getRelease_fc2com(htmlcode2): #
|
||||
html=etree.fromstring(htmlcode2,etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getCover_fc2com(htmlcode2): #获取厂商 #
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[1]/span/img/@src')).strip(" ['']")
|
||||
return 'http:' + result
|
||||
def getOutline_fc2com(htmlcode2): #获取番号 #
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
|
||||
return result
|
||||
def getTag_fc2com(number): #获取番号
|
||||
htmlcode = str(bytes(ADC_function.get_html('http://adult.contents.fc2.com/api/v4/article/'+number+'/tag?'),'utf-8').decode('unicode-escape'))
|
||||
result = re.findall('"tag":"(.*?)"', htmlcode)
|
||||
return result
|
||||
def getYear_fc2com(release):
|
||||
try:
|
||||
result = re.search('\d{4}',release).group()
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
|
||||
def main(number):
|
||||
try:
|
||||
htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/'+number+'/')
|
||||
htmlcode = ADC_function.get_html('https://fc2club.com//html/FC2-' + number + '.html')
|
||||
actor = getActor(htmlcode)
|
||||
if getActor(htmlcode) == '':
|
||||
actor = 'FC2系列'
|
||||
dic = {
|
||||
'title': getTitle(htmlcode),
|
||||
'studio': getStudio(htmlcode),
|
||||
'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
|
||||
'outline': '',#getOutline(htmlcode2),
|
||||
'runtime': getYear(getRelease(htmlcode)),
|
||||
'director': getStudio(htmlcode),
|
||||
'actor': actor,
|
||||
'release': getRelease(number),
|
||||
'number': 'FC2-'+number,
|
||||
'label': '',
|
||||
'cover': getCover(htmlcode,number,htmlcode2),
|
||||
'imagecut': 0,
|
||||
'tag': getTag(htmlcode),
|
||||
'actor_photo':'',
|
||||
'website': 'https://fc2club.com//html/FC2-' + number + '.html',
|
||||
'source':'https://fc2club.com//html/FC2-' + number + '.html',
|
||||
}
|
||||
if dic['title'] == '':
|
||||
htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/' + number + '/',cookies={'wei6H':'1'})
|
||||
actor = getActor(htmlcode)
|
||||
if getActor(htmlcode) == '':
|
||||
actor = 'FC2系列'
|
||||
dic = {
|
||||
'title': getTitle_fc2com(htmlcode2),
|
||||
'studio': getStudio_fc2com(htmlcode2),
|
||||
'year': '', # str(re.search('\d{4}',getRelease(number)).group()),
|
||||
'outline': getOutline_fc2com(htmlcode2),
|
||||
'runtime': getYear_fc2com(getRelease(htmlcode2)),
|
||||
'director': getStudio_fc2com(htmlcode2),
|
||||
'actor': actor,
|
||||
'release': getRelease_fc2com(number),
|
||||
'number': 'FC2-' + number,
|
||||
'cover': getCover_fc2com(htmlcode2),
|
||||
'imagecut': 0,
|
||||
'tag': getTag_fc2com(number),
|
||||
'label': '',
|
||||
'actor_photo': '',
|
||||
'website': 'http://adult.contents.fc2.com/article/' + number + '/',
|
||||
'source': 'http://adult.contents.fc2.com/article/' + number + '/',
|
||||
}
|
||||
except Exception as e:
|
||||
# (TODO) better handle this
|
||||
# print(e)
|
||||
dic = {"title": ""}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
|
||||
return js
|
||||
|
||||
|
||||
#print(main('1252953'))
|
||||
import re
|
||||
from lxml import etree#need install
|
||||
import json
|
||||
import ADC_function
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
def getTitle(htmlcode): #获取厂商
|
||||
#print(htmlcode)
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h3/text()')).strip(" ['']")
|
||||
result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
|
||||
#print(result2)
|
||||
return result2
|
||||
def getActor(htmlcode):
|
||||
try:
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[5]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
def getStudio(htmlcode): #获取厂商
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getNum(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
|
||||
#print(result)
|
||||
return result
|
||||
def getRelease(htmlcode2): #
|
||||
#a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
|
||||
html=etree.fromstring(htmlcode2,etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getCover(htmlcode,number,htmlcode2): #获取厂商 #
|
||||
#a = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id=' + str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") + '&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
|
||||
if result == '':
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']")
|
||||
return 'https://fc2club.com' + result2
|
||||
return 'http:' + result
|
||||
def getOutline(htmlcode2): #获取番号 #
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[1]/div[2]/div[2]/div[1]/div/article/section[4]/p/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
|
||||
return result
|
||||
def getTag(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
|
||||
return result.strip(" ['']").replace("'",'').replace(' ','')
|
||||
def getYear(release):
|
||||
try:
|
||||
result = re.search('\d{4}',release).group()
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getTitle_fc2com(htmlcode): #获取厂商
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/h3/text()')[0]
|
||||
return result
|
||||
def getActor_fc2com(htmlcode):
|
||||
try:
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')[0]
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
def getStudio_fc2com(htmlcode): #获取厂商
|
||||
try:
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
def getNum_fc2com(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getRelease_fc2com(htmlcode2): #
|
||||
html=etree.fromstring(htmlcode2,etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getCover_fc2com(htmlcode2): #获取厂商 #
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[1]/span/img/@src')).strip(" ['']")
|
||||
return 'http:' + result
|
||||
def getOutline_fc2com(htmlcode2): #获取番号 #
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
|
||||
return result
|
||||
def getTag_fc2com(number): #获取番号
|
||||
htmlcode = str(bytes(ADC_function.get_html('http://adult.contents.fc2.com/api/v4/article/'+number+'/tag?'),'utf-8').decode('unicode-escape'))
|
||||
result = re.findall('"tag":"(.*?)"', htmlcode)
|
||||
return result
|
||||
def getYear_fc2com(release):
|
||||
try:
|
||||
result = re.search('\d{4}',release).group()
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
|
||||
def main(number):
|
||||
try:
|
||||
htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/'+number+'/')
|
||||
htmlcode = ADC_function.get_html('https://fc2club.com//html/FC2-' + number + '.html')
|
||||
actor = getActor(htmlcode)
|
||||
if getActor(htmlcode) == '':
|
||||
actor = 'FC2系列'
|
||||
dic = {
|
||||
'title': getTitle(htmlcode),
|
||||
'studio': getStudio(htmlcode),
|
||||
'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
|
||||
'outline': '',#getOutline(htmlcode2),
|
||||
'runtime': getYear(getRelease(htmlcode)),
|
||||
'director': getStudio(htmlcode),
|
||||
'actor': actor,
|
||||
'release': getRelease(number),
|
||||
'number': 'FC2-'+number,
|
||||
'label': '',
|
||||
'cover': getCover(htmlcode,number,htmlcode2),
|
||||
'imagecut': 0,
|
||||
'tag': getTag(htmlcode),
|
||||
'actor_photo':'',
|
||||
'website': 'https://fc2club.com//html/FC2-' + number + '.html',
|
||||
'source':'https://fc2club.com//html/FC2-' + number + '.html',
|
||||
}
|
||||
if dic['title'] == '':
|
||||
htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/' + number + '/',cookies={'wei6H':'1'})
|
||||
actor = getActor(htmlcode)
|
||||
if getActor(htmlcode) == '':
|
||||
actor = 'FC2系列'
|
||||
dic = {
|
||||
'title': getTitle_fc2com(htmlcode2),
|
||||
'studio': getStudio_fc2com(htmlcode2),
|
||||
'year': '', # str(re.search('\d{4}',getRelease(number)).group()),
|
||||
'outline': getOutline_fc2com(htmlcode2),
|
||||
'runtime': getYear_fc2com(getRelease(htmlcode2)),
|
||||
'director': getStudio_fc2com(htmlcode2),
|
||||
'actor': actor,
|
||||
'release': getRelease_fc2com(number),
|
||||
'number': 'FC2-' + number,
|
||||
'cover': getCover_fc2com(htmlcode2),
|
||||
'imagecut': 0,
|
||||
'tag': getTag_fc2com(number),
|
||||
'label': '',
|
||||
'actor_photo': '',
|
||||
'website': 'http://adult.contents.fc2.com/article/' + number + '/',
|
||||
'source': 'http://adult.contents.fc2.com/article/' + number + '/',
|
||||
}
|
||||
except Exception as e:
|
||||
# (TODO) better handle this
|
||||
# print(e)
|
||||
dic = {"title": ""}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
|
||||
return js
|
||||
|
||||
|
||||
#print(main('1252953'))
|
||||
|
||||
276
javbus.py
276
javbus.py
@@ -1,138 +1,138 @@
|
||||
import re
|
||||
from pyquery import PyQuery as pq#need install
|
||||
from lxml import etree#need install
|
||||
from bs4 import BeautifulSoup#need install
|
||||
import json
|
||||
from ADC_function import *
|
||||
|
||||
def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'star-name'})
|
||||
d={}
|
||||
for i in a:
|
||||
l=i.a['href']
|
||||
t=i.get_text()
|
||||
html = etree.fromstring(get_html(l), etree.HTMLParser())
|
||||
p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
|
||||
p2={t:p}
|
||||
d.update(p2)
|
||||
return d
|
||||
def getTitle(htmlcode): #获取标题
|
||||
doc = pq(htmlcode)
|
||||
title=str(doc('div.container h3').text()).replace(' ','-')
|
||||
try:
|
||||
title2 = re.sub('n\d+-','',title)
|
||||
return title2
|
||||
except:
|
||||
return title
|
||||
def getStudio(htmlcode): #获取厂商
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
def getYear(htmlcode): #获取年份
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getCover(htmlcode): #获取封面链接
|
||||
doc = pq(htmlcode)
|
||||
image = doc('a.bigImage')
|
||||
return image.attr('href')
|
||||
def getRelease(htmlcode): #获取出版日期
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getRuntime(htmlcode): #获取分钟
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find(text=re.compile('分鐘'))
|
||||
return a
|
||||
def getActor(htmlcode): #获取女优
|
||||
b=[]
|
||||
soup=BeautifulSoup(htmlcode,'lxml')
|
||||
a=soup.find_all(attrs={'class':'star-name'})
|
||||
for i in a:
|
||||
b.append(i.get_text())
|
||||
return b
|
||||
def getNum(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getDirector(htmlcode): #获取导演
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
def getOutline(htmlcode): #获取演员
|
||||
doc = pq(htmlcode)
|
||||
result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
|
||||
return result
|
||||
def getSerise(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
def getTag(htmlcode): # 获取演员
|
||||
tag = []
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'genre'})
|
||||
for i in a:
|
||||
if 'onmouseout' in str(i):
|
||||
continue
|
||||
tag.append(i.get_text())
|
||||
return tag
|
||||
|
||||
|
||||
def main(number):
|
||||
try:
|
||||
htmlcode = get_html('https://www.javbus.com/' + number)
|
||||
try:
|
||||
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
except:
|
||||
dww_htmlcode = ''
|
||||
dic = {
|
||||
'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
|
||||
'studio': getStudio(htmlcode),
|
||||
'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
|
||||
'outline': getOutline(dww_htmlcode),
|
||||
'runtime': getRuntime(htmlcode),
|
||||
'director': getDirector(htmlcode),
|
||||
'actor': getActor(htmlcode),
|
||||
'release': getRelease(htmlcode),
|
||||
'number': getNum(htmlcode),
|
||||
'cover': getCover(htmlcode),
|
||||
'imagecut': 1,
|
||||
'tag': getTag(htmlcode),
|
||||
'label': getSerise(htmlcode),
|
||||
'actor_photo': getActorPhoto(htmlcode),
|
||||
'website': 'https://www.javbus.com/' + number,
|
||||
'source' : 'javbus.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
except:
|
||||
return main_uncensored(number)
|
||||
|
||||
def main_uncensored(number):
|
||||
htmlcode = get_html('https://www.javbus.com/' + number)
|
||||
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
if getTitle(htmlcode) == '':
|
||||
htmlcode = get_html('https://www.javbus.com/' + number.replace('-','_'))
|
||||
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
dic = {
|
||||
'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
|
||||
'studio': getStudio(htmlcode),
|
||||
'year': getYear(htmlcode),
|
||||
'outline': getOutline(dww_htmlcode),
|
||||
'runtime': getRuntime(htmlcode),
|
||||
'director': getDirector(htmlcode),
|
||||
'actor': getActor(htmlcode),
|
||||
'release': getRelease(htmlcode),
|
||||
'number': getNum(htmlcode),
|
||||
'cover': getCover(htmlcode),
|
||||
'tag': getTag(htmlcode),
|
||||
'label': getSerise(htmlcode),
|
||||
'imagecut': 0,
|
||||
'actor_photo': '',
|
||||
'website': 'https://www.javbus.com/' + number,
|
||||
'source': 'javbus.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
import re
|
||||
from pyquery import PyQuery as pq#need install
|
||||
from lxml import etree#need install
|
||||
from bs4 import BeautifulSoup#need install
|
||||
import json
|
||||
from ADC_function import *
|
||||
|
||||
def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'star-name'})
|
||||
d={}
|
||||
for i in a:
|
||||
l=i.a['href']
|
||||
t=i.get_text()
|
||||
html = etree.fromstring(get_html(l), etree.HTMLParser())
|
||||
p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
|
||||
p2={t:p}
|
||||
d.update(p2)
|
||||
return d
|
||||
def getTitle(htmlcode): #获取标题
|
||||
doc = pq(htmlcode)
|
||||
title=str(doc('div.container h3').text()).replace(' ','-')
|
||||
try:
|
||||
title2 = re.sub('n\d+-','',title)
|
||||
return title2
|
||||
except:
|
||||
return title
|
||||
def getStudio(htmlcode): #获取厂商
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
def getYear(htmlcode): #获取年份
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getCover(htmlcode): #获取封面链接
|
||||
doc = pq(htmlcode)
|
||||
image = doc('a.bigImage')
|
||||
return image.attr('href')
|
||||
def getRelease(htmlcode): #获取出版日期
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getRuntime(htmlcode): #获取分钟
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find(text=re.compile('分鐘'))
|
||||
return a
|
||||
def getActor(htmlcode): #获取女优
|
||||
b=[]
|
||||
soup=BeautifulSoup(htmlcode,'lxml')
|
||||
a=soup.find_all(attrs={'class':'star-name'})
|
||||
for i in a:
|
||||
b.append(i.get_text())
|
||||
return b
|
||||
def getNum(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getDirector(htmlcode): #获取导演
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
def getOutline(htmlcode): #获取演员
|
||||
doc = pq(htmlcode)
|
||||
result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
|
||||
return result
|
||||
def getSerise(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
def getTag(htmlcode): # 获取演员
|
||||
tag = []
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'genre'})
|
||||
for i in a:
|
||||
if 'onmouseout' in str(i):
|
||||
continue
|
||||
tag.append(i.get_text())
|
||||
return tag
|
||||
|
||||
|
||||
def main(number):
|
||||
try:
|
||||
htmlcode = get_html('https://www.javbus.com/' + number)
|
||||
try:
|
||||
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
except:
|
||||
dww_htmlcode = ''
|
||||
dic = {
|
||||
'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
|
||||
'studio': getStudio(htmlcode),
|
||||
'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
|
||||
'outline': getOutline(dww_htmlcode),
|
||||
'runtime': getRuntime(htmlcode),
|
||||
'director': getDirector(htmlcode),
|
||||
'actor': getActor(htmlcode),
|
||||
'release': getRelease(htmlcode),
|
||||
'number': getNum(htmlcode),
|
||||
'cover': getCover(htmlcode),
|
||||
'imagecut': 1,
|
||||
'tag': getTag(htmlcode),
|
||||
'label': getSerise(htmlcode),
|
||||
'actor_photo': getActorPhoto(htmlcode),
|
||||
'website': 'https://www.javbus.com/' + number,
|
||||
'source' : 'javbus.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
except:
|
||||
return main_uncensored(number)
|
||||
|
||||
def main_uncensored(number):
|
||||
htmlcode = get_html('https://www.javbus.com/' + number)
|
||||
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
if getTitle(htmlcode) == '':
|
||||
htmlcode = get_html('https://www.javbus.com/' + number.replace('-','_'))
|
||||
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
dic = {
|
||||
'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
|
||||
'studio': getStudio(htmlcode),
|
||||
'year': getYear(htmlcode),
|
||||
'outline': getOutline(dww_htmlcode),
|
||||
'runtime': getRuntime(htmlcode),
|
||||
'director': getDirector(htmlcode),
|
||||
'actor': getActor(htmlcode),
|
||||
'release': getRelease(htmlcode),
|
||||
'number': getNum(htmlcode),
|
||||
'cover': getCover(htmlcode),
|
||||
'tag': getTag(htmlcode),
|
||||
'label': getSerise(htmlcode),
|
||||
'imagecut': 0,
|
||||
'actor_photo': '',
|
||||
'website': 'https://www.javbus.com/' + number,
|
||||
'source': 'javbus.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
|
||||
246
javdb.py
246
javdb.py
@@ -1,123 +1,123 @@
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
def getTitle(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result = html.xpath("/html/body/section/div/h2/strong/text()")[0]
|
||||
return result
|
||||
def getActor(a): # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',').replace(',', ', ')
|
||||
def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
|
||||
a = actor.split(',')
|
||||
d={}
|
||||
for i in a:
|
||||
p={i:''}
|
||||
d.update(p)
|
||||
return d
|
||||
def getStudio(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
def getRuntime(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').rstrip('mi')
|
||||
def getLabel(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
def getNum(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result2 + result1).strip('+')
|
||||
def getYear(getRelease):
|
||||
try:
|
||||
result = str(re.search('\d{4}', getRelease).group())
|
||||
return result
|
||||
except:
|
||||
return getRelease
|
||||
def getRelease(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+')
|
||||
def getTag(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',')
|
||||
def getCover_small(a, index=0):
|
||||
# same issue mentioned below,
|
||||
# javdb sometime returns multiple results
|
||||
# DO NOT just get the firt one, get the one with correct index number
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index]
|
||||
if not 'https' in result:
|
||||
result = 'https:' + result
|
||||
return result
|
||||
def getCover(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath("//div[@class='column column-video-cover']/a/img/@src")).strip(" ['']")
|
||||
return result
|
||||
def getDirector(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
def getOutline(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
|
||||
return result
|
||||
def main(number):
|
||||
try:
|
||||
number = number.upper()
|
||||
query_result = get_html('https://javdb.com/search?q=' + number + '&f=all')
|
||||
html = etree.fromstring(query_result, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
# 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 = html.xpath('//*[@id="videos"]/div/div/a/@href')
|
||||
ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
|
||||
correct_url = urls[ids.index(number)]
|
||||
detail_page = get_html('https://javdb.com' + correct_url)
|
||||
dic = {
|
||||
'actor': getActor(detail_page),
|
||||
'title': getTitle(detail_page),
|
||||
'studio': getStudio(detail_page),
|
||||
'outline': getOutline(detail_page),
|
||||
'runtime': getRuntime(detail_page),
|
||||
'director': getDirector(detail_page),
|
||||
'release': getRelease(detail_page),
|
||||
'number': getNum(detail_page),
|
||||
'cover': getCover(detail_page),
|
||||
'cover_small': getCover_small(query_result, index=ids.index(number)),
|
||||
'imagecut': 3,
|
||||
'tag': getTag(detail_page),
|
||||
'label': getLabel(detail_page),
|
||||
'year': getYear(getRelease(detail_page)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': getActorPhoto(getActor(detail_page)),
|
||||
'website': 'https://javdb.com' + correct_url,
|
||||
'source': 'javdb.py',
|
||||
}
|
||||
except Exception as e:
|
||||
# print(e)
|
||||
dic = {"title": ""}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
# main('DV-1562')
|
||||
# input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。")
|
||||
#print(main('ipx-292'))
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
def getTitle(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result = html.xpath("/html/body/section/div/h2/strong/text()")[0]
|
||||
return result
|
||||
def getActor(a): # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',').replace(',', ', ')
|
||||
def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
|
||||
a = actor.split(',')
|
||||
d={}
|
||||
for i in a:
|
||||
p={i:''}
|
||||
d.update(p)
|
||||
return d
|
||||
def getStudio(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
def getRuntime(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').rstrip('mi')
|
||||
def getLabel(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
def getNum(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result2 + result1).strip('+')
|
||||
def getYear(getRelease):
|
||||
try:
|
||||
result = str(re.search('\d{4}', getRelease).group())
|
||||
return result
|
||||
except:
|
||||
return getRelease
|
||||
def getRelease(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+')
|
||||
def getTag(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',')
|
||||
def getCover_small(a, index=0):
|
||||
# same issue mentioned below,
|
||||
# javdb sometime returns multiple results
|
||||
# DO NOT just get the firt one, get the one with correct index number
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index]
|
||||
if not 'https' in result:
|
||||
result = 'https:' + result
|
||||
return result
|
||||
def getCover(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath("//div[@class='column column-video-cover']/a/img/@src")).strip(" ['']")
|
||||
return result
|
||||
def getDirector(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']")
|
||||
result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']")
|
||||
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
|
||||
def getOutline(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
|
||||
return result
|
||||
def main(number):
|
||||
try:
|
||||
number = number.upper()
|
||||
query_result = get_html('https://javdb.com/search?q=' + number + '&f=all')
|
||||
html = etree.fromstring(query_result, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
# 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 = html.xpath('//*[@id="videos"]/div/div/a/@href')
|
||||
ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
|
||||
correct_url = urls[ids.index(number)]
|
||||
detail_page = get_html('https://javdb.com' + correct_url)
|
||||
dic = {
|
||||
'actor': getActor(detail_page),
|
||||
'title': getTitle(detail_page),
|
||||
'studio': getStudio(detail_page),
|
||||
'outline': getOutline(detail_page),
|
||||
'runtime': getRuntime(detail_page),
|
||||
'director': getDirector(detail_page),
|
||||
'release': getRelease(detail_page),
|
||||
'number': getNum(detail_page),
|
||||
'cover': getCover(detail_page),
|
||||
'cover_small': getCover_small(query_result, index=ids.index(number)),
|
||||
'imagecut': 3,
|
||||
'tag': getTag(detail_page),
|
||||
'label': getLabel(detail_page),
|
||||
'year': getYear(getRelease(detail_page)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': getActorPhoto(getActor(detail_page)),
|
||||
'website': 'https://javdb.com' + correct_url,
|
||||
'source': 'javdb.py',
|
||||
}
|
||||
except Exception as e:
|
||||
# print(e)
|
||||
dic = {"title": ""}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
# main('DV-1562')
|
||||
# input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。")
|
||||
#print(main('ipx-292'))
|
||||
|
||||
222
mgstage.py
222
mgstage.py
@@ -1,111 +1,111 @@
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
def getTitle(a):
|
||||
try:
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="center_column"]/div[1]/h1/text()')).strip(" ['']")
|
||||
return result.replace('/', ',')
|
||||
except:
|
||||
return ''
|
||||
def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
|
||||
result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
result2=str(html.xpath('//th[contains(text(),"出演：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
return str(result1+result2).strip('+').replace("', '",'').replace('"','').replace('/',',')
|
||||
def getStudio(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
|
||||
result1=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
result2=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
return str(result1+result2).strip('+').replace("', '",'').replace('"','')
|
||||
def getRuntime(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
return str(result1 + result2).strip('+').rstrip('mi')
|
||||
def getLabel(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
|
||||
def getNum(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+')
|
||||
def getYear(getRelease):
|
||||
try:
|
||||
result = str(re.search('\d{4}',getRelease).group())
|
||||
return result
|
||||
except:
|
||||
return getRelease
|
||||
def getRelease(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+')
|
||||
def getTag(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','')
|
||||
def getCover(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="center_column"]/div[1]/div[1]/div/div/h2/img/@src')).strip(" ['']")
|
||||
# /html/body/div[2]/article[2]/div[1]/div[1]/div/div/h2/img/@src
|
||||
return result
|
||||
def getDirector(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
|
||||
def getOutline(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//p/text()')).strip(" ['']")
|
||||
return result
|
||||
def main(number2):
|
||||
number=number2.upper()
|
||||
htmlcode=str(get_html('https://www.mgstage.com/product/product_detail/'+str(number)+'/',cookies={'adc':'1'}))
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
|
||||
b = str(soup.find(attrs={'id': 'introduction'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
|
||||
print(b)
|
||||
dic = {
|
||||
'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''),
|
||||
'studio': getStudio(a),
|
||||
'outline': getOutline(b),
|
||||
'runtime': getRuntime(a),
|
||||
'director': getDirector(a),
|
||||
'actor': getActor(a),
|
||||
'release': getRelease(a),
|
||||
'number': getNum(a),
|
||||
'cover': getCover(htmlcode),
|
||||
'imagecut': 0,
|
||||
'tag': getTag(a),
|
||||
'label':getLabel(a),
|
||||
'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': '',
|
||||
'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
|
||||
'source': 'mgstage.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
#print(htmlcode)
|
||||
|
||||
print(main('SIRO-3607'))
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
# import sys
|
||||
# import io
|
||||
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
|
||||
|
||||
def getTitle(a):
|
||||
try:
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="center_column"]/div[1]/h1/text()')).strip(" ['']")
|
||||
return result.replace('/', ',')
|
||||
except:
|
||||
return ''
|
||||
def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
|
||||
result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
result2=str(html.xpath('//th[contains(text(),"出演：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
return str(result1+result2).strip('+').replace("', '",'').replace('"','').replace('/',',')
|
||||
def getStudio(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
|
||||
result1=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
result2=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
return str(result1+result2).strip('+').replace("', '",'').replace('"','')
|
||||
def getRuntime(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
|
||||
return str(result1 + result2).strip('+').rstrip('mi')
|
||||
def getLabel(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
|
||||
def getNum(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+')
|
||||
def getYear(getRelease):
|
||||
try:
|
||||
result = str(re.search('\d{4}',getRelease).group())
|
||||
return result
|
||||
except:
|
||||
return getRelease
|
||||
def getRelease(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+')
|
||||
def getTag(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','')
|
||||
def getCover(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="center_column"]/div[1]/div[1]/div/div/h2/img/@src')).strip(" ['']")
|
||||
# /html/body/div[2]/article[2]/div[1]/div[1]/div/div/h2/img/@src
|
||||
return result
|
||||
def getDirector(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
|
||||
'\\n')
|
||||
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
|
||||
def getOutline(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//p/text()')).strip(" ['']")
|
||||
return result
|
||||
def main(number2):
|
||||
number=number2.upper()
|
||||
htmlcode=str(get_html('https://www.mgstage.com/product/product_detail/'+str(number)+'/',cookies={'adc':'1'}))
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
|
||||
b = str(soup.find(attrs={'id': 'introduction'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
|
||||
print(b)
|
||||
dic = {
|
||||
'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''),
|
||||
'studio': getStudio(a),
|
||||
'outline': getOutline(b),
|
||||
'runtime': getRuntime(a),
|
||||
'director': getDirector(a),
|
||||
'actor': getActor(a),
|
||||
'release': getRelease(a),
|
||||
'number': getNum(a),
|
||||
'cover': getCover(htmlcode),
|
||||
'imagecut': 0,
|
||||
'tag': getTag(a),
|
||||
'label':getLabel(a),
|
||||
'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': '',
|
||||
'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
|
||||
'source': 'mgstage.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
#print(htmlcode)
|
||||
|
||||
print(main('SIRO-3607'))
|
||||
|
||||
Reference in New Issue
Block a user