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

将欧美全部归类到无码

Browse Source
This commit is contained in:
lededev
2022-04-10 15:29:46 +08:00
parent 02692becfe
commit e5bc900b40
2 changed files with 16 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
WebCrawler/javbus.py
View File

@@ -88,7 +88,8 @@ def getUncensored(html):
return bool(x) return bool(x)
def main_uncensored(number): def main_uncensored(number):
htmlcode = get_html('https://www.javbus.com/ja/' + number) w_number = number.replace('.', '-')
htmlcode = get_html('https://www.javbus.red/' + w_number)
if "<title>404 Page Not Found" in htmlcode: if "<title>404 Page Not Found" in htmlcode:
raise Exception('404 page not found') raise Exception('404 page not found')
lx = etree.fromstring(htmlcode, etree.HTMLParser()) lx = etree.fromstring(htmlcode, etree.HTMLParser())
@@ -97,7 +98,7 @@ def main_uncensored(number):
'title': title, 'title': title,
'studio': getStudioJa(lx), 'studio': getStudioJa(lx),
'year': getYear(lx), 'year': getYear(lx),
'outline': getOutline(number, title), 'outline': getOutline(w_number, title),
'runtime': getRuntime(lx), 'runtime': getRuntime(lx),
'director': getDirectorJa(lx), 'director': getDirectorJa(lx),
'actor': getActor(lx), 'actor': getActor(lx),
@@ -109,10 +110,10 @@ def main_uncensored(number):
'label': getSeriseJa(lx), 'label': getSeriseJa(lx),
'imagecut': 0, 'imagecut': 0,
# 'actor_photo': '', # 'actor_photo': '',
'website': 'https://www.javbus.com/ja/' + number, 'website': 'https://www.javbus.red/' + w_number,
'source': 'javbus.py', 'source': 'javbus.py',
'series': getSeriseJa(lx), 'series': getSeriseJa(lx),
'无码': getUncensored(lx) '无码': True
} }
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js return js
@@ -174,12 +175,13 @@ def main(number):
if __name__ == "__main__" : if __name__ == "__main__" :
config.G_conf_override['debug_mode:switch'] = True config.G_conf_override['debug_mode:switch'] = True
print(main('ABP-888')) # print(main('ABP-888'))
print(main('ABP-960')) # print(main('ABP-960'))
print(main('ADV-R0624')) # 404 # print(main('ADV-R0624')) # 404
print(main('MMNT-010')) # print(main('MMNT-010'))
print(main('ipx-292')) # print(main('ipx-292'))
print(main('CEMD-011')) # print(main('CEMD-011'))
print(main('CJOD-278')) # print(main('CJOD-278'))
print(main('BrazzersExxtra.21.02.01'))
print(main('100221_001')) print(main('100221_001'))
print(main('AVSW-061')) print(main('AVSW-061'))

4
WebCrawler/javdb.py
View File

@@ -180,7 +180,8 @@ def getUserRating(html):
except: except:
return return
def getUncensored(html): def getUncensored(html):
x = html.xpath('//strong[contains(text(),"類別")]/../span/a[contains(@href,"/tags/uncensored?")]') x = html.xpath('//strong[contains(text(),"類別")]/../span/a[contains(@href,"/tags/uncensored?")'
' or contains(@href,"/tags/western?")]')
return bool(x) return bool(x)
def main(number): def main(number):
@@ -342,3 +343,4 @@ if __name__ == "__main__":
# print(main('EBOD-646')) # print(main('EBOD-646'))
# print(main('LOVE-262')) # print(main('LOVE-262'))
print(main('ABP-890')) print(main('ABP-890'))
print(main('blacked.14.12.08'))