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

下载演员头像到.actors目录，KODI用；不联网的Jellyfin封面图文件名

Browse Source
This commit is contained in:
lededev
2022-04-24 19:50:29 +08:00
parent 42d9986c16
commit 2a3c50a2dd
9 changed files with 149 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
WebCrawler/airav.py
View File

@@ -202,8 +202,7 @@ def main(number):
'tag': getTag(htmlcode),
# 使用javbus
'label': getSerise(javbus_json),
# 妈的，airav不提供作者图片
# 'actor_photo': getActorPhoto(javbus_json),
'actor_photo': getActorPhoto(javbus_json),
'website': 'https://www.airav.wiki/video/' + number,
'source': 'airav.py',
# 使用javbus
@@ -224,6 +223,8 @@ def main(number):
if __name__ == '__main__':
config.getInstance().set_override("actor_photo:download_for_kodi=1")
config.getInstance().set_override("debug_mode:switch=1")
print(main('ADV-R0624')) # javbus页面返回404, airav有数据
print(main('ADN-188')) # 一人
print(main('CJOD-278')) # 多人 javbus演员名称采用日语假名，airav采用日文汉字

3
WebCrawler/carib.py
View File

@@ -36,12 +36,13 @@ def main(number: str) -> json:
'extrafanart': get_extrafanart(lx),
'label': get_series(lx),
'imagecut': 1,
# 'actor_photo': get_actor_photo(lx, session),
'website': f'{G_SITE}/moviepages/{number}/index.html',
'source': 'carib.py',
'series': get_series(lx),
'无码': True
}
if config.getInstance().download_actor_photo_for_kodi():
dic['actor_photo'] = get_actor_photo(lx, session)
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )
return js

6
WebCrawler/fc2.py
View File

@@ -3,6 +3,7 @@ sys.path.append('../')
import re
from lxml import etree#need install
import json
import config
import ADC_function
from WebCrawler.crawler import *
# import sys
@@ -77,4 +78,7 @@ def main(number):
return js
if __name__ == '__main__':
print(main('FC2-2182382'))
config.getInstance().set_override("debug_mode:switch=1")
#print(main('FC2-2182382'))
#print(main('FC2-607854'))
print(main('FC2-2787433'))

36
WebCrawler/javbus.py
View File

@@ -8,16 +8,14 @@ from WebCrawler.storyline import getStoryline
import inspect
def getActorPhoto(html):
actors = html.xpath('//div[@class="star-name"]/a')
d={}
actors = html.xpath('//div[@class="star-name"]/../a/img')
d = {}
for i in actors:
url=i.attrib['href']
t=i.attrib['title']
html = etree.fromstring(get_html(url), etree.HTMLParser())
p=urljoin("https://www.javbus.com",
str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']"))
p2={t:p}
d.update(p2)
p = i.attrib['src']
if "nowprinting.gif" in p:
continue
t = i.attrib['title']
d[t] = urljoin("https://www.javbus.com", p)
return d
def getTitle(html): #获取标题
title = str(html.xpath('/html/head/title/text()')[0])
@@ -109,7 +107,7 @@ def main_uncensored(number):
'extrafanart': getExtrafanart(htmlcode),
'label': getSeriseJa(lx),
'imagecut': 0,
# 'actor_photo': '',
'actor_photo': getActorPhoto(lx),
'website': 'https://www.javbus.red/' + w_number,
'source': 'javbus.py',
'series': getSeriseJa(lx),
@@ -152,7 +150,7 @@ def main(number):
'tag': getTag(lx),
'extrafanart': getExtrafanart(htmlcode),
'label': getSerise(lx),
# 'actor_photo': getActorPhoto(lx),
'actor_photo': getActorPhoto(lx),
'website': 'https://www.javbus.com/' + number,
'source': 'javbus.py',
'series': getSerise(lx),
@@ -174,14 +172,16 @@ def main(number):
return js
if __name__ == "__main__" :
config.getInstance().set_override("storyline:switch=0")
config.getInstance().set_override("actor_photo:download_for_kodi=1")
config.getInstance().set_override("debug_mode:switch=1")
# print(main('ABP-888'))
# print(main('ABP-960'))
# print(main('ADV-R0624')) # 404
# print(main('MMNT-010'))
# print(main('ipx-292'))
# print(main('CEMD-011'))
# print(main('CJOD-278'))
print(main('ABP-888'))
print(main('ABP-960'))
print(main('ADV-R0624')) # 404
print(main('MMNT-010'))
print(main('ipx-292'))
print(main('CEMD-011'))
print(main('CJOD-278'))
print(main('BrazzersExxtra.21.02.01'))
print(main('100221_001'))
print(main('AVSW-061'))

40
WebCrawler/javdb.py
View File

@@ -30,13 +30,9 @@ def getActor(html):
return r
def getaphoto(url, session):
html_page = session.get(url).text if session is not None else get_html(url)
img_prether = re.compile(r'<span class\=\"avatar\" style\=\"background\-image\: url\((.*?)\)')
img_url = img_prether.findall(html_page)
if img_url:
return img_url[0]
else:
return ''
html_page = session.get(url).text
img_url = re.findall(r'<span class\=\"avatar\" style\=\"background\-image\: url\((.*?)\)', html_page)
return img_url[0] if img_url else ''
def getActorPhoto(html, javdb_site, session):
actorall = html.xpath('//strong[contains(text(),"演員:")]/../span/a[starts-with(@href,"/actors/")]')
@@ -44,9 +40,18 @@ def getActorPhoto(html, javdb_site, session):
return {}
a = getActor(html)
actor_photo = {}
if not session:
session = get_html_session()
for i in actorall:
if i.text in a:
actor_photo[i.text] = getaphoto(urljoin(f'https://{javdb_site}.com', i.attrib['href']), session)
x = re.findall(r'/actors/(.*)', i.attrib['href'], re.A)
if not len(x) or not len(x[0]) or i.text not in a:
continue
actor_id = x[0]
pic_url = f"https://c1.jdbstatic.com/avatars/{actor_id[:2].lower()}/{actor_id}.jpg"
if not session.head(pic_url).ok:
pic_url = getaphoto(urljoin(f'https://{javdb_site}.com', i.attrib['href']), session)
if len(pic_url):
actor_photo[i.text] = pic_url
return actor_photo
def getStudio(a, html):
@@ -300,7 +305,6 @@ def main(number):
'tag': getTag(lx),
'label': getLabel(lx),
'year': getYear(detail_page), # str(re.search('\d{4}',getRelease(a)).group()),
# 'actor_photo': getActorPhoto(lx, javdb_site, session),
'website': urljoin('https://javdb.com', correct_url),
'source': 'javdb.py',
'series': getSeries(lx),
@@ -316,6 +320,8 @@ def main(number):
dic['series'] = dic['studio']
if not dic['label']:
dic['label'] = dic['studio']
if config.getInstance().download_actor_photo_for_kodi():
dic['actor_photo'] = getActorPhoto(lx, javdb_site, session)
except Exception as e:
@@ -328,19 +334,21 @@ def main(number):
# 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。")
if __name__ == "__main__":
config.getInstance().set_override("storyline:switch=0")
config.getInstance().set_override("actor_photo:download_for_kodi=1")
config.getInstance().set_override("debug_mode:switch=1")
# print(main('blacked.20.05.30'))
# print(main('AGAV-042'))
# print(main('BANK-022'))
print(main('AGAV-042'))
print(main('BANK-022'))
print(main('070116-197'))
# print(main('093021_539')) # 没有剧照 片商pacopacomama
print(main('093021_539')) # 没有剧照 片商pacopacomama
#print(main('FC2-2278260'))
# print(main('FC2-735670'))
# print(main('FC2-1174949')) # not found
#print(main('MVSD-439'))
print(main('MVSD-439'))
# print(main('EHM0001')) # not found
#print(main('FC2-2314275'))
# print(main('EBOD-646'))
# print(main('LOVE-262'))
print(main('EBOD-646'))
print(main('LOVE-262'))
print(main('ABP-890'))
print(main('blacked.14.12.08'))

27
WebCrawler/xcity.py
View File

@@ -23,19 +23,16 @@ def getActor(browser):
def getActorPhoto(browser):
htmla = browser.page.select('#avodDetails > div > div.frame > div.content > div > ul.profileCL > li.credit-links > a')
t = {}
for i in htmla:
p = {i.text.strip(): i['href']}
t.update(p)
t = {i.text.strip(): i['href'] for i in htmla}
o = {}
for k, v in t.items():
r = browser.open_relative(v)
if r.ok:
pic = browser.page.select_one('#avidolDetails > div > div.frame > div > p > img')
p = {k: urljoin(browser.url, pic['src'])}
else:
p = {k, ''}
o.update(p)
if not r.ok:
continue
pic = browser.page.select_one('#avidolDetails > div > div.frame > div > p > img')
if 'noimage.gif' in pic['src']:
continue
o[k] = urljoin(browser.url, pic['src'])
return o
@@ -205,11 +202,12 @@ def main(number):
'tag': getTag(lx),
'label': getLabel(lx),
'year': getYear(getRelease(lx)), # str(re.search('\d{4}',getRelease(a)).group()),
# 'actor_photo': getActorPhoto(browser),
'website': url,
'source': 'xcity.py',
'series': getSeries(lx),
}
if config.getInstance().download_actor_photo_for_kodi():
dic['actor_photo'] = getActorPhoto(browser)
except Exception as e:
if config.getInstance().debug():
print(e)
@@ -219,6 +217,9 @@ def main(number):
return js
if __name__ == '__main__':
config.getInstance().set_override("storyline:switch=0")
config.getInstance().set_override("actor_photo:download_for_kodi=1")
config.getInstance().set_override("debug_mode:switch=1")
print(main('RCTD-288'))
#print(main('VNDS-2624'))
#print(main('ABP-345'))
print(main('VNDS-2624'))
print(main('ABP-345'))