bacow/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Clean out of used modules

Browse Source
This commit is contained in:
yoshiko2
2022-05-11 22:51:10 +08:00
parent b3058a6f1f
commit 2096c0908c
15 changed files with 0 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
WebCrawler/airav.py
View File

@@ -1,10 +1,6 @@
import sys
sys.path.append('../')
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 *
from WebCrawler import javbus

3
WebCrawler/avsox.py
View File

@@ -1,8 +1,5 @@
import sys
sys.path.append('..')
import re
from lxml import etree
import json
from ADC_function import *
from WebCrawler.storyline import getStoryline
from WebCrawler.crawler import *

2
WebCrawler/carib.py
View File

@@ -1,8 +1,6 @@
import sys
sys.path.append('../')
import json
from lxml import html
import re
from ADC_function import *
from WebCrawler.storyline import getStoryline

14
WebCrawler/dlsite.py
View File

@@ -4,20 +4,6 @@ import json
import sys
sys.path.append('../')
from ADC_function import *
# import sys
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
#print(get_html('https://www.dlsite.com/maniax/work/=/product_id/VJ013152.html'))
#title /html/head/title/text()
#studio //th[contains(text(),"ブランド名")]/../td/span[1]/a/text()
#release //th[contains(text(),"販売日")]/../td/a/text()
#story //th[contains(text(),"シナリオ")]/../td/a/text()
#senyo //th[contains(text(),"声優")]/../td/a/text()
#tag //th[contains(text(),"ジャンル")]/../td/div/a/text()
#jianjie //*[@id="main_inner"]/div[3]/text()
#photo //*[@id="work_left"]/div/div/div[2]/div/div[1]/div[1]/ul/li/img/@src
#https://www.dlsite.com/maniax/work/=/product_id/VJ013152.html
def getTitle(html):
result = str(html.xpath('/html/head/title/text()')[0])

7
WebCrawler/fanza.py
View File

@@ -2,17 +2,10 @@
# -*- coding: utf-8 -*-
import sys
sys.path.append('../')
import json
import re
from urllib.parse import urlencode
from lxml import etree
from ADC_function import *
from WebCrawler.crawler import *
# import sys
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
class fanzaCrawler(Crawler):
def getFanzaString(self,string):

4
WebCrawler/fc2.py
View File

@@ -1,14 +1,10 @@
import sys
sys.path.append('../')
import re
from lxml import etree#need install
import json
import config
import ADC_function
from WebCrawler.crawler import *
# import sys
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<ul class=\"items_article_SampleImagesArea\"[\s\S]*?</ul>')

12
WebCrawler/fc2club.py
View File

@@ -1,12 +1,8 @@
import sys
sys.path.append('../')
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_fc2com(htmlcode): #获取标题
html = etree.fromstring(htmlcode,etree.HTMLParser())
@@ -44,14 +40,6 @@ def getCover_fc2com(htmlcode2): #获取img #
imgUrl = imgUrl.replace('../','https://fc2club.net/')
print(imgUrl)
return imgUrl
# def getOutline_fc2com(htmlcode2): #获取番号 #
# xpath_html = etree.fromstring(htmlcode2, etree.HTMLParser())
# path = str(xpath_html.xpath('//*[@id="top"]/div[1]/section[4]/iframe/@src')).strip(" ['']")
# html = etree.fromstring(ADC_function.get_html('https://adult.contents.fc2.com/'+path), etree.HTMLParser())
# print('https://adult.contents.fc2.com'+path)
# print(ADC_function.get_html('https://adult.contents.fc2.com'+path,cookies={'wei6H':'1'}))
# result = str(html.xpath('/html/body/div/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
# return result
def getTag_fc2com(htmlcode): #获取tag
html = etree.fromstring(htmlcode,etree.HTMLParser())
a = html.xpath('//*[@class="show-top-grids"]/div[1]/h5[4]/a')

2
WebCrawler/gcolle.py
View File

@@ -3,8 +3,6 @@ sys.path.append('../')
from WebCrawler.crawler import *
from ADC_function import *
from lxml import etree
def main(number):
save_cookies = False

3
WebCrawler/javbus.py
View File

@@ -1,8 +1,5 @@
import sys
sys.path.append('../')
import re
from lxml import etree#need install
import json
from ADC_function import *
from WebCrawler.storyline import getStoryline
import inspect

18
WebCrawler/javdb.py
View File

@@ -1,12 +1,7 @@
import sys
sys.path.append('../')
import re
from lxml import etree
import json
from ADC_function import *
from WebCrawler.storyline import getStoryline
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
def getTitle(html):
browser_title = str(html.xpath("/html/head/title/text()")[0])
@@ -55,10 +50,6 @@ def getActorPhoto(html, javdb_site, session):
return actor_photo
def getStudio(a, html):
# html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
# result1 = str(html.xpath('//strong[contains(text(),"片商")]/../span/text()')).strip(" ['']")
# result2 = str(html.xpath('//strong[contains(text(),"片商")]/../span/a/text()')).strip(" ['']")
# return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
patherr = re.compile(r'<strong>片商\:</strong>[\s\S]*?<a href=\".*?>(.*?)</a></span>')
pianshang = patherr.findall(a)
if pianshang:
@@ -85,11 +76,6 @@ def getNum(html):
result2 = str(html.xpath('//strong[contains(text(),"番號")]/../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
patherr = re.compile(r'<strong>日期\:</strong>\s*?.*?<span class="value">(.*?)\-.*?</span>')
dates = patherr.findall(getRelease)
if dates:
@@ -99,10 +85,6 @@ def getYear(getRelease):
return result
def getRelease(a):
# html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
# result1 = str(html.xpath('//strong[contains(text(),"時間")]/../span/text()')).strip(" ['']")
# result2 = str(html.xpath('//strong[contains(text(),"時間")]/../span/a/text()')).strip(" ['']")
# return str(result1 + result2).strip('+')
patherr = re.compile(r'<strong>日期\:</strong>\s*?.*?<span class="value">(.*?)</span>')
dates = patherr.findall(a)
if dates:

3
WebCrawler/madou.py
View File

@@ -1,8 +1,5 @@
import sys
sys.path.append('../')
from bs4 import BeautifulSoup # need install
from lxml import etree # need install
from pyquery import PyQuery as pq # need install
from ADC_function import *
import json
import re

6
WebCrawler/mgstage.py
View File

@@ -1,14 +1,8 @@
import sys
sys.path.append('../')
import re
from lxml import etree
import json
from bs4 import BeautifulSoup
from ADC_function import *
from WebCrawler.crawler import *
# import sys
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
class MgsCrawler(Crawler):
def getMgsString(self, _xpath):

5
WebCrawler/mv91.py
View File

@@ -1,10 +1,5 @@
import sys
sys.path.append('../')
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 *

2
WebCrawler/storyline.py
View File

@@ -1,7 +1,5 @@
import sys
sys.path.append('../')
import re
import json
import builtins
from ADC_function import *
from lxml.html import fromstring

5
WebCrawler/xcity.py
View File

@@ -1,12 +1,7 @@
import sys
sys.path.append('../')
import re
from lxml import etree
import json
from ADC_function import *
from WebCrawler.storyline import getStoryline
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
def getTitle(html):
result = html.xpath('//*[@id="program_detail_title"]/text()')[0]