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'))

32
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')
actors = html.xpath('//div[@class="star-name"]/../a/img')
d = {}
for i in actors:
url=i.attrib['href']
p = i.attrib['src']
if "nowprinting.gif" in p:
continue
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)
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'))

25
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:
if not r.ok:
continue
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 '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'))

3
config.ini
View File

@@ -131,3 +131,6 @@ aspect_ratio=2.12
[jellyfin]
multi_part_fanart=0
[actor_photo]
download_for_kodi=0

3
config.py
View File

@@ -397,6 +397,9 @@ class Config:
def jellyfin_multi_part_fanart(self) -> bool:
return self.conf.getboolean("jellyfin", "multi_part_fanart", fallback=False)
def download_actor_photo_for_kodi(self) -> bool:
return self.conf.getboolean("actor_photo", "download_for_kodi", fallback=False)
@staticmethod
def _exit(sec: str) -> None:
print("[-] Read config error! Please check the {} section in config.ini", sec)

83
core.py
View File

@@ -172,6 +172,7 @@ def download_file_with_filename(url, filename, path, filepath):
moveFailedFolder(filepath)
return
def trailer_download(trailer, leak_word, c_word, hack_word, number, path, filepath):
if download_file_with_filename(trailer, number + leak_word + c_word + hack_word + '-trailer.mp4', path, filepath) == 'failed':
return
@@ -187,12 +188,50 @@ def trailer_download(trailer, leak_word, c_word, hack_word, number, path, filepa
return
print('[+]Video Downloaded!', path + '/' + number + leak_word + c_word + hack_word + '-trailer.mp4')
def actor_photo_download(actors, save_dir, number):
if not isinstance(actors, dict) or not len(actors) or not len(save_dir):
return
save_dir = Path(save_dir)
if not save_dir.is_dir():
return
conf = config.getInstance()
actors_dir = save_dir / '.actors'
download_only_missing_images = conf.download_only_missing_images()
dn_list = []
for actor_name, url in actors.items():
res = re.match(r'^http.*(\.\w+)$', url, re.A)
if not res:
continue
ext = res.group(1)
pic_fullpath = actors_dir / f'{actor_name}{ext}'
if download_only_missing_images and not file_not_exist_or_empty(pic_fullpath):
continue
dn_list.append((url, pic_fullpath))
if not len(dn_list):
return
parallel = min(len(dn_list), conf.extrafanart_thread_pool_download())
if parallel > 100:
print('[!]Warrning: Parallel download thread too large may cause website ban IP!')
result = parallel_download_files(dn_list, parallel)
failed = 0
for i, r in enumerate(result):
if not r:
failed += 1
print(f"[-]Actor photo '{dn_list[i][0]}' to '{dn_list[i][1]}' download failed!")
if failed: # 非致命错误，电影不移入失败文件夹，将来可以用模式3补齐
print(f"[-]Failed downloaded {failed}/{len(result)} actor photo for [{number}] to '{actors_dir}', you may retry run mode 3 later.")
else:
print(f"[+]Successfully downloaded {len(result)} actor photo.")
# 剧照下载成功，否则移动到failed
def extrafanart_download(data, path, number, filepath):
if config.getInstance().extrafanart_thread_pool_download():
return extrafanart_download_threadpool(data, path, number)
extrafanart_download_one_by_one(data, path, filepath)
def extrafanart_download_one_by_one(data, path, filepath):
tm_start = time.perf_counter()
j = 1
@@ -252,12 +291,14 @@ def extrafanart_download_threadpool(url_list, save_dir, number):
if conf.debug():
print(f'[!]Extrafanart download ThreadPool mode runtime {time.perf_counter() - tm_start:.3f}s')
def image_ext(url):
try:
return os.path.splitext(url)[-1]
except:
return ".jpg"
# 封面是否下载成功，否则移动到failed
def image_download(cover, fanart_path, thumb_path, path, filepath):
full_filepath = os.path.join(path, fanart_path)
@@ -676,12 +717,14 @@ def core_main_no_net_op(movie_path, number):
cn_sub = ''
hack = ''
hack_word = ''
ext = '.jpg'
imagecut = 1
multi = False
part = ''
path = str(Path(movie_path).parent)
if re.search('[-_]CD\d+', movie_path, re.IGNORECASE):
part = re.findall('[-_]CD\d+', movie_path, re.IGNORECASE)[0].upper()
multi = True
if re.search(r'[-_]C(\.\w+$|-\w+)|\d+ch(\.\w+$|-\w+)', movie_path,
re.I) or '中文' in movie_path or '字幕' in movie_path:
cn_sub = '1'
@@ -696,19 +739,24 @@ def core_main_no_net_op(movie_path, number):
hack_word = "-hack"
prestr = f"{number}{leak_word}{c_word}{hack_word}"
full_nfo = Path(path) / f"{prestr}{part}.nfo"
if full_nfo.is_file():
if full_nfo.read_text(encoding='utf-8').find(r'<tag>无码</tag>') >= 0:
uncensored = 1
try:
nfo_xml = etree.parse(full_nfo)
nfo_fanart_path = nfo_xml.xpath('//fanart/text()')[0]
ext = Path(nfo_fanart_path).suffix
except:
return
else:
return
fanart_path = f"{prestr}-fanart{ext}"
poster_path = f"{prestr}-poster{ext}"
thumb_path = f"{prestr}-thumb{ext}"
full_fanart_path = os.path.join(path, fanart_path)
full_poster_path = os.path.join(path, poster_path)
full_thumb_path = os.path.join(path, thumb_path)
full_nfo = Path(path) / f"{prestr}{part}.nfo"
if full_nfo.is_file():
if full_nfo.read_text(encoding='utf-8').find(r'<tag>无码</tag>') >= 0:
uncensored = 1
else:
return
if not all(os.path.isfile(f) for f in (full_fanart_path, full_thumb_path)):
return
@@ -717,6 +765,9 @@ def core_main_no_net_op(movie_path, number):
if conf.is_watermark():
add_mark(full_poster_path, full_thumb_path, cn_sub, leak, uncensored, hack)
if multi and conf.jellyfin_multi_part_fanart():
linkImage(path, number, part, leak_word, c_word, hack_word, ext)
def core_main(movie_path, number_th, oCC):
conf = config.getInstance()
@@ -808,16 +859,17 @@ def core_main(movie_path, number_th, oCC):
# 下载预告片
if conf.is_trailer() and json_data.get('trailer'):
trailer_download(json_data.get('trailer'), leak_word, c_word, hack_word, number, path, movie_path)
except:
pass
try:
# 下载剧照 data, path, filepath
if conf.is_extrafanart() and json_data.get('extrafanart'):
extrafanart_download(json_data.get('extrafanart'), path, number, movie_path)
# 下载演员头像 KODI .actors 目录位置
if conf.download_actor_photo_for_kodi():
actor_photo_download(json_data.get('actor_photo'), path, number)
except:
pass
# 裁剪图
cutImage(imagecut, path, fanart_path, poster_path, bool(conf.face_uncensored_only() and not uncensored))
@@ -857,6 +909,7 @@ def core_main(movie_path, number_th, oCC):
image_download( cover, fanart_path, thumb_path, path, movie_path)
if not multi_part or part.lower() == '-cd1':
try:
# 下载预告片
if conf.is_trailer() and json_data.get('trailer'):
trailer_download(json_data.get('trailer'), leak_word, c_word, hack_word, number, path, movie_path)
@@ -865,6 +918,12 @@ def core_main(movie_path, number_th, oCC):
if conf.is_extrafanart() and json_data.get('extrafanart'):
extrafanart_download(json_data.get('extrafanart'), path, number, movie_path)
# 下载演员头像 KODI .actors 目录位置
if conf.download_actor_photo_for_kodi():
actor_photo_download(json_data.get('actor_photo'), path, number)
except:
pass
# 裁剪图
cutImage(imagecut, path, fanart_path, poster_path, bool(conf.face_uncensored_only() and not uncensored))