From f3f8c649c964f656f95fd7bee340cdf7c50d12d9 Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Tue, 4 Aug 2020 16:09:02 +0800
Subject: [PATCH 01/11] update BiliBiliIE
---
youtube_dl/extractor/bilibili.py | 439 +++++++++++++++++++++++--------
1 file changed, 322 insertions(+), 117 deletions(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 4dc597e16..5928dcea3 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -3,6 +3,7 @@ from __future__ import unicode_literals
import hashlib
import re
+import json
from .common import InfoExtractor
from ..compat import (
@@ -26,12 +27,11 @@ from ..utils import (
class BiliBiliIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
- (?:(?:www|bangumi)\.)?
+ (?:(?:www)\.)?
bilibili\.(?:tv|com)/
(?:
(?:
- video/[aA][vV]|
- anime/(?P<anime_id>\d+)/play\#
+ video/[aA][vV]
)(?P<id_bv>\d+)|
video/[bB][vV](?P<id>[^/?#&]+)
)
@@ -120,141 +120,346 @@ class BiliBiliIE(InfoExtractor):
else:
raise ExtractorError('Can\'t extract Bangumi episode ID')
+ def _getfps(self,s:str)->int:
+ "convert fps to int"
+ if s.isnumeric() :
+ return int(s)
+ else :
+ r=re.search(r"([0-9]+)/([0-9]+)",s)
+ if r!=None :
+ r=r.groups()
+ return int(r[0])/int(r[1])
+ else :
+ return 0
+
+ def _calculate_size(self,durl:list) -> int :
+ "Calculate total file size."
+ s=0
+ for i in durl :
+ s=s+i['size']
+ return s
+
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') or mobj.group('id_bv')
- anime_id = mobj.group('anime_id')
+ query=compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+ part=None
+ if 'p' in query and str(query['p'][0]).isnumeric() :
+ part=int(query['p'][0])
+
+ #Set Cookies need to parse the Links.
+ self._set_cookie(domain=".bilibili.com",name="CURRENT_QUALITY",value="120")#Set default video quality
+ self._set_cookie(domain=".bilibili.com",name="CURRENT_FNVAL",value="16")
+ self._set_cookie(domain=".bilibili.com",name="laboratory",value="1-1")#Use new webpage API
+ self._set_cookie(domain=".bilibili.com",name="stardustvideo",value="1")
+
webpage = self._download_webpage(url, video_id)
- if 'anime/' not in url:
- cid = self._search_regex(
- r'\bcid(?:["\']:|=)(\d+)', webpage, 'cid',
- default=None
- ) or compat_parse_qs(self._search_regex(
- [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
- r'EmbedPlayer\([^)]+,\s*\\"([^"]+)\\"\)',
- r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
- webpage, 'player parameters'))['cid'][0]
- else:
- if 'no_bangumi_tip' not in smuggled_data:
- self.to_screen('Downloading episode %s. To download all videos in anime %s, re-run youtube-dl with %s' % (
- video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id)))
- headers = {
- 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
- 'Referer': url
- }
- headers.update(self.geo_verification_headers())
+ video_info=re.search(r"window\.__INITIAL_STATE__=([^;]+)",webpage,re.I)
+ if video_info != None :
+ video_info=json.loads(video_info.groups()[0])
+ else :
+ self._report_error("") #TODO Should redirect to Bangumi episode ID.
+ #https://api.bilibili.com/x/web-interface/view/detail?bvid=&aid=&jsonp=jsonp have redirect links.
+ video_data=video_info['videoData']
+ uploader_data=video_info['upData']
+ aid=video_data['aid']
+ bvid=video_data['bvid']
+ video_count=video_data['videos']
- js = self._download_json(
- 'http://bangumi.bilibili.com/web_api/get_source', video_id,
- data=urlencode_postdata({'episode_id': video_id}),
- headers=headers)
- if 'result' not in js:
- self._report_error(js)
- cid = js['result']['cid']
+ tags_info=self._download_json(
+ f"https://api.bilibili.com/x/web-interface/view/detail/tag?aid={aid}",video_id,
+ 'Geting video tags.','Unable to get Login/User Information.')
+ if tags_info['code']!=0 :
+ self._report_error(tags_info)
+ tags_info=tags_info['data']
+ tags=[]
+ for i in tags_info :
+ tags.append(i['tag_name'])
+
+ user_info=self._download_json("https://api.bilibili.com/x/web-interface/nav",video_id,
+ "Geting Login/User Information.","Unable to get Login/User Information.")
+ if user_info['code']!=0 and user_info['code']!=-101 :
+ self._report_error(user_info)
+ user_info=user_info['data']
+ is_login=user_info['isLogin']
+ if is_login:
+ is_vip=user_info['vipStatus']
+ else :
+ is_vip=0
+ is_durl=False # If return the durl Stream, this will be true
- headers = {
- 'Referer': url
+ info={
+ 'id':video_id,
+ 'title':video_data['title'],
+ 'description':video_data['desc'],
+ 'timestamp':video_data['ctime'],
+ 'thumbnail':video_data['pic'],
+ 'uploader':uploader_data['name'],
+ 'uploader_id':uploader_data['mid'],
+ 'duration':video_data['duration'],
+ 'webpage_url':f'https://www.bilibili.com/video/av{aid}',
+ 'categories':[video_data['tname']],
+ 'view_count':video_data['stat']['viewseo'],
+ 'comment_count':video_data['stat']['reply'],
+ 'tags':tags
}
- headers.update(self.geo_verification_headers())
- entries = []
+ if video_count==1 :
+ info.update({'alt_title':video_data['pages'][0]['part']})
- RENDITIONS = ('qn=80&quality=80&type=', 'quality=2&type=mp4')
- for num, rendition in enumerate(RENDITIONS, start=1):
- payload = 'appkey=%s&cid=%s&otype=json&%s' % (self._APP_KEY, cid, rendition)
- sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
+ new_api=True #Parse video links from webpage first.
+ first=True #First Part of List
+ entries=[]
- video_info = self._download_json(
- 'http://interface.bilibili.com/v2/playurl?%s&sign=%s' % (payload, sign),
- video_id, note='Downloading video info page',
- headers=headers, fatal=num == len(RENDITIONS))
-
- if not video_info:
+ for part_info in video_data['pages'] :
+ if part != None and part_info["page"]!=part :
continue
-
- if 'durl' not in video_info:
- if num < len(RENDITIONS):
+ uri=f'https://www.bilibili.com/video/av{aid}?p={part_info["page"]}'
+ if first :
+ first=False
+ else :
+ webpage=self._download_webpage(uri,f"{video_id} Part{part_info['page']}")
+ headers={'referer':uri}
+ if new_api:
+ play_info=re.search(r"window\.__playinfo__=([^<]+)",webpage,re.I) #Get video links from webpage.
+ if play_info != None :
+ play_info=json.loads(play_info.groups()[0])
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ else :
+ new_api=False
+ play_info=self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn=120&otype=json&bvid={bvid}&fnver=0&fnval=16",
+ f"{video_id} Part{part_info['page']}",
+ "Geting video links.",
+ "Unable to get video links.")
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ else :
+ play_info=self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn=120&otype=json&bvid={bvid}&fnver=0&fnval=16",
+ f"{video_id} Part{part_info['page']}",
+ "Geting video links.",
+ "Unable to get video links.")
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ if 'durl' in play_info: # Stream for flv player
+ if video_count > 1 and len(play_info['durl']) > 1 and part==None :
+ self.report_warning(
+ f"There are multiply FLV files in this part. Please input \"{uri}\" to extract it.",
+ f"{video_id} Part{part_info['page']}")
continue
- self._report_error(video_info)
-
- for idx, durl in enumerate(video_info['durl']):
- formats = [{
- 'url': durl['url'],
- 'filesize': int_or_none(durl['size']),
- }]
- for backup_url in durl.get('backup_url', []):
- formats.append({
- 'url': backup_url,
- # backup URLs have lower priorities
- 'preference': -2 if 'hd.mp4' in backup_url else -3,
+ is_durl=True
+ if video_count>1:
+ info.update({
+ 'title':f"{info['title']} - {part_info['part']}",
+ 'id':f"{video_id} P{part_info['page']}"
})
-
- for a_format in formats:
- a_format.setdefault('http_headers', {}).update({
- 'Referer': url,
+ video_quality=play_info['quality']
+ accept_video_quality_desc=play_info['accept_description']
+ accept_video_quality=play_info['accept_quality']
+ video_desc_dict={}
+ for i in range(len(accept_video_quality)) :
+ video_desc_dict.update({
+ accept_video_quality[i]:accept_video_quality_desc[i]
})
+ video_formats={video_quality:play_info['durl']}
+ video_formats_size={video_quality:self._calculate_size(play_info['durl'])} #Total Filesize Dict
+ durl_length=[len(play_info['durl'])]
+ for video_q in accept_video_quality :
+ if video_q not in video_formats :
+ if new_api :
+ self._set_cookie(domain=".bilibili.com",name="CURRENT_QUALITY",value=f"{video_q}")
+ webpage=self._download_webpage(uri,
+ f"{video_id} Part{part_info['page']}",
+ f"Geting video links for format id : {video_q}.",
+ f"Unable to get video links for format id : {video_q}.")
+ play_info=re.search(r"window\.__playinfo__=([^<]+)",webpage,re.I) #Get video links from webpage.
+ if play_info != None :
+ play_info=json.loads(play_info.groups()[0])
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ else :
+ new_api=False
+ play_info=self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",f"{video_id} Part{part_info['page']}",
+ f"Geting video links for format id : {video_q}.",
+ f"Unable to get video links for format id : {video_q}.")
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ else :
+ play_info=self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",f"{video_id} Part{part_info['page']}",
+ f"Geting video links for format id : {video_q}.",
+ f"Unable to get video links for format id : {video_q}.")
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ if 'durl' in play_info :
+ video_formats[play_info["quality"]]=play_info['durl']
+ video_formats_size[play_info["quality"]]=self._calculate_size(play_info['durl'])
+ durl_length.append(len(play_info['durl']))
+ for i in range(max(durl_length)) :
+ entry={}
+ entry.update(info)
+ entry.update({'id':f"{info['id']} Part{i+1}"})
+ formats_output=[]
+ for video_q in accept_video_quality :
+ durl=video_formats[video_q]
+ if i < len(durl) :
+ video_format=durl[i]
+ formats_output.append({
+ "url":video_format['url'],
+ "format_id":f"{video_q}",
+ "ext":"flv",
+ "http_headers":headers,
+ "filesize":video_format['size']
+ })
+ entry['formats']=formats_output
+ entries.append(entry)
+ elif 'dash' in play_info : # Stream for dash player
+ video_quality=play_info['quality']
+ accept_video_quality_desc=play_info['accept_description']
+ accept_video_quality=play_info['accept_quality']
+ accept_audio_quality=[]
+ dash=play_info['dash']
+ video_quality_list=[]
+ video_desc_dict={}
+ for i in range(len(accept_video_quality)) :
+ video_desc_dict.update({
+ accept_video_quality[i]:accept_video_quality_desc[i]
+ })
+ video_formats={}
+ for video_format in dash['video'] :
+ if video_format['codecs'].startswith('hev') : #Let format id increase 1 to distinguish codec
+ video_quality_list.append(video_format['id']+1)
+ video_formats[video_format['id']+1]=video_format
+ else :
+ video_quality_list.append(video_format['id'])
+ video_formats[video_format['id']]=video_format
+ bs=True #Try to get all video formats
+ while bs:
+ bs=False
+ for video_q in accept_video_quality :
+ if video_q not in video_formats:
+ if not is_login and video_q <=32 :
+ bs=True
+ elif is_vip<1 and video_q<=80 and video_q!=74 :
+ bs=True
+ elif is_vip>0:
+ bs=True
+ if new_api :
+ self._set_cookie(domain=".bilibili.com",name="CURRENT_QUALITY",value=f"{video_q}")
+ webpage=self._download_webpage(uri,
+ f"{video_id} Part{part_info['page']}",
+ f"Geting video links for format id : {video_q}.",
+ f"Unable to get video links for format id : {video_q}.")
+ play_info=re.search(r"window\.__playinfo__=([^<]+)",webpage,re.I) #Get video links from webpage.
+ if play_info != None :
+ play_info=json.loads(play_info.groups()[0])
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ else :
+ new_api=False
+ play_info=self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",f"{video_id} Part{part_info['page']}",
+ f"Geting video links for format id : {video_q}.",
+ f"Unable to get video links for format id : {video_q}.")
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ else :
+ play_info=self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",
+ f"{video_id} Part{part_info['page']}",
+ f"Geting video links for format id : {video_q}.",
+ f"Unable to get video links for format id : {video_q}.")
+ if play_info['code']!=0 :
+ self._report_error(play_info)
+ play_info=play_info['data']
+ if 'dash' in play_info:
+ for video_format in play_info['dash']['video'] :
+ if video_format['codecs'].startswith('hev') : #Let format id increase 1 to distinguish codec
+ video_format_q=video_format['id']+1
+ else :
+ video_format_q=video_format['id']
+ if video_format_q not in video_formats :
+ video_quality_list.append(video_format_q)
+ video_formats[video_format_q]=video_format
+ bs=True
+ break
+ self._set_cookie(domain=".bilibili.com",name="CURRENT_QUALITY",value="120")
+ entry={}
+ entry.update(info)
+ formats_output=[]
+ for i in video_quality_list :
+ video_format=video_formats[i]
+ formats_output.append(
+ {"url":video_format['base_url'],
+ "ext":"mp4",
+ "format_note":video_desc_dict[video_format['id']],
+ "format_id":f"{i}",
+ "vcodec":video_format['codecs'],
+ "fps":self._getfps(video_format['frame_rate']),
+ "width":video_format['width'],
+ "height":video_format['height'],
+ "http_headers":headers
+ })
+ if 'audio' in dash and dash['audio']!=None :
+ for audio_format in dash['audio'] :
+ accept_audio_quality.append(audio_format['id'])
+ video_formats[audio_format['id']]=audio_format
+ accept_audio_quality.sort(reverse=True)
+ for audio_quality in accept_audio_quality :
+ audio_format=video_formats[audio_quality]
+ formats_output.append({
+ "url":audio_format["base_url"],
+ "format_id":f"{audio_format['id']}",
+ "ext":"mp4",
+ "acodec":audio_format['codecs'],
+ "http_headers":headers
+ })
+ entry.update({"formats":formats_output})
+ if video_count > 1 :
+ entry.update({"title":f"{info['title']} - {part_info['part']}"})
+ entry.update({"id":f"{video_id} P{part_info['page']}"})
+ entries.append(entry)
- self._sort_formats(formats)
-
- entries.append({
- 'id': '%s_part%s' % (video_id, idx),
- 'duration': float_or_none(durl.get('length'), 1000),
- 'formats': formats,
+ if video_count > 1 :
+ if len(entries) == 1 and not is_durl:
+ info.update({
+ 'formats':entries[0]['formats'],
+ 'id':entries[0]['id']
})
- break
-
- title = self._html_search_regex(
- ('<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
- '(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
- group='title')
- description = self._html_search_meta('description', webpage)
- timestamp = unified_timestamp(self._html_search_regex(
- r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time',
- default=None) or self._html_search_meta(
- 'uploadDate', webpage, 'timestamp', default=None))
- thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
-
- # TODO 'view_count' requires deobfuscating Javascript
- info = {
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'timestamp': timestamp,
- 'thumbnail': thumbnail,
- 'duration': float_or_none(video_info.get('timelength'), scale=1000),
- }
-
- uploader_mobj = re.search(
- r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]*>(?P<name>[^<]+)',
- webpage)
- if uploader_mobj:
+ return info
info.update({
- 'uploader': uploader_mobj.group('name'),
- 'uploader_id': uploader_mobj.group('id'),
+ "_type":'multi_video',
+ "entries":entries
})
- if not info.get('uploader'):
- info['uploader'] = self._html_search_meta(
- 'author', webpage, 'uploader', default=None)
-
- for entry in entries:
- entry.update(info)
-
- if len(entries) == 1:
- return entries[0]
- else:
- for idx, entry in enumerate(entries):
- entry['id'] = '%s_part%d' % (video_id, (idx + 1))
-
- return {
- '_type': 'multi_video',
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'entries': entries,
- }
+ return info
+ else :
+ if not is_durl:
+ return entries[0]
+ else :
+ if len(entries)>1 :
+ info.update({
+ "_type":'multi_video',
+ "entries":entries
+ })
+ else :
+ info.update({
+ "formats":entries[0]['formats']
+ })
+ return info
class BiliBiliBangumiIE(InfoExtractor):
From 5c5c58243b4b176701894971b1b1c237cbeb57eb Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Tue, 4 Aug 2020 16:49:38 +0800
Subject: [PATCH 02/11] formatting the code
---
youtube_dl/extractor/bilibili.py | 495 +++++++++++++++----------------
1 file changed, 245 insertions(+), 250 deletions(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 5928dcea3..e8bcfd099 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -1,26 +1,21 @@
# coding: utf-8
from __future__ import unicode_literals
-import hashlib
import re
import json
from .common import InfoExtractor
from ..compat import (
- compat_parse_qs,
compat_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
- float_or_none,
parse_iso8601,
smuggle_url,
str_or_none,
strip_jsonp,
- unified_timestamp,
unsmuggle_url,
- urlencode_postdata,
)
@@ -120,23 +115,23 @@ class BiliBiliIE(InfoExtractor):
else:
raise ExtractorError('Can\'t extract Bangumi episode ID')
- def _getfps(self,s:str)->int:
+ def _getfps(self, s: str) -> int:
"convert fps to int"
- if s.isnumeric() :
+ if s.isnumeric():
return int(s)
- else :
- r=re.search(r"([0-9]+)/([0-9]+)",s)
- if r!=None :
- r=r.groups()
- return int(r[0])/int(r[1])
- else :
+ else:
+ r = re.search(r"([0-9]+)/([0-9]+)", s)
+ if r is not None:
+ r = r.groups()
+ return int(r[0]) / int(r[1])
+ else:
return 0
-
- def _calculate_size(self,durl:list) -> int :
+
+ def _calculate_size(self, durl: list) -> int:
"Calculate total file size."
- s=0
- for i in durl :
- s=s+i['size']
+ s = 0
+ for i in durl:
+ s = s + i['size']
return s
def _real_extract(self, url):
@@ -144,320 +139,320 @@ class BiliBiliIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') or mobj.group('id_bv')
- query=compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
- part=None
- if 'p' in query and str(query['p'][0]).isnumeric() :
- part=int(query['p'][0])
+ query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+ part = None
+ if 'p' in query and str(query['p'][0]).isnumeric():
+ part = int(query['p'][0])
- #Set Cookies need to parse the Links.
- self._set_cookie(domain=".bilibili.com",name="CURRENT_QUALITY",value="120")#Set default video quality
- self._set_cookie(domain=".bilibili.com",name="CURRENT_FNVAL",value="16")
- self._set_cookie(domain=".bilibili.com",name="laboratory",value="1-1")#Use new webpage API
- self._set_cookie(domain=".bilibili.com",name="stardustvideo",value="1")
+ # Set Cookies need to parse the Links.
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value="120") # Set default video quality
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_FNVAL", value="16")
+ self._set_cookie(domain=".bilibili.com", name="laboratory", value="1-1") # Use new webpage API
+ self._set_cookie(domain=".bilibili.com", name="stardustvideo", value="1")
webpage = self._download_webpage(url, video_id)
- video_info=re.search(r"window\.__INITIAL_STATE__=([^;]+)",webpage,re.I)
- if video_info != None :
- video_info=json.loads(video_info.groups()[0])
- else :
- self._report_error("") #TODO Should redirect to Bangumi episode ID.
- #https://api.bilibili.com/x/web-interface/view/detail?bvid=&aid=&jsonp=jsonp have redirect links.
- video_data=video_info['videoData']
- uploader_data=video_info['upData']
- aid=video_data['aid']
- bvid=video_data['bvid']
- video_count=video_data['videos']
+ video_info = re.search(r"window\.__INITIAL_STATE__=([^;]+)", webpage, re.I)
+ if video_info is not None:
+ video_info = json.loads(video_info.groups()[0])
+ else:
+ self._report_error("") # TODO Should redirect to Bangumi episode ID.
+ # https://api.bilibili.com/x/web-interface/view/detail?bvid=&aid=&jsonp=jsonp have redirect links.
+ video_data = video_info['videoData']
+ uploader_data = video_info['upData']
+ aid = video_data['aid']
+ bvid = video_data['bvid']
+ video_count = video_data['videos']
- tags_info=self._download_json(
- f"https://api.bilibili.com/x/web-interface/view/detail/tag?aid={aid}",video_id,
- 'Geting video tags.','Unable to get Login/User Information.')
- if tags_info['code']!=0 :
+ tags_info = self._download_json(
+ f"https://api.bilibili.com/x/web-interface/view/detail/tag?aid={aid}", video_id,
+ 'Geting video tags.', 'Unable to get Login/User Information.')
+ if tags_info['code'] != 0:
self._report_error(tags_info)
- tags_info=tags_info['data']
- tags=[]
- for i in tags_info :
+ tags_info = tags_info['data']
+ tags = []
+ for i in tags_info:
tags.append(i['tag_name'])
-
- user_info=self._download_json("https://api.bilibili.com/x/web-interface/nav",video_id,
- "Geting Login/User Information.","Unable to get Login/User Information.")
- if user_info['code']!=0 and user_info['code']!=-101 :
- self._report_error(user_info)
- user_info=user_info['data']
- is_login=user_info['isLogin']
- if is_login:
- is_vip=user_info['vipStatus']
- else :
- is_vip=0
- is_durl=False # If return the durl Stream, this will be true
- info={
- 'id':video_id,
- 'title':video_data['title'],
- 'description':video_data['desc'],
- 'timestamp':video_data['ctime'],
- 'thumbnail':video_data['pic'],
- 'uploader':uploader_data['name'],
- 'uploader_id':uploader_data['mid'],
- 'duration':video_data['duration'],
- 'webpage_url':f'https://www.bilibili.com/video/av{aid}',
- 'categories':[video_data['tname']],
- 'view_count':video_data['stat']['viewseo'],
- 'comment_count':video_data['stat']['reply'],
- 'tags':tags
+ user_info = self._download_json("https://api.bilibili.com/x/web-interface/nav", video_id,
+ "Geting Login/User Information.", "Unable to get Login/User Information.")
+ if user_info['code'] != 0 and user_info['code'] != -101:
+ self._report_error(user_info)
+ user_info = user_info['data']
+ is_login = user_info['isLogin']
+ if is_login:
+ is_vip = user_info['vipStatus']
+ else:
+ is_vip = 0
+ is_durl = False # If return the durl Stream, this will be true
+
+ info = {
+ 'id': video_id,
+ 'title': video_data['title'],
+ 'description': video_data['desc'],
+ 'timestamp': video_data['ctime'],
+ 'thumbnail': video_data['pic'],
+ 'uploader': uploader_data['name'],
+ 'uploader_id': uploader_data['mid'],
+ 'duration': video_data['duration'],
+ 'webpage_url': f'https://www.bilibili.com/video/av{aid}',
+ 'categories': [video_data['tname']],
+ 'view_count': video_data['stat']['viewseo'],
+ 'comment_count': video_data['stat']['reply'],
+ 'tags': tags
}
- if video_count==1 :
- info.update({'alt_title':video_data['pages'][0]['part']})
+ if video_count == 1:
+ info.update({'alt_title': video_data['pages'][0]['part']})
- new_api=True #Parse video links from webpage first.
- first=True #First Part of List
- entries=[]
+ new_api = True # Parse video links from webpage first.
+ first = True # First Part of List
+ entries = []
- for part_info in video_data['pages'] :
- if part != None and part_info["page"]!=part :
+ for part_info in video_data['pages']:
+ if part is not None and part_info["page"] != part:
continue
- uri=f'https://www.bilibili.com/video/av{aid}?p={part_info["page"]}'
- if first :
- first=False
- else :
- webpage=self._download_webpage(uri,f"{video_id} Part{part_info['page']}")
- headers={'referer':uri}
+ uri = f'https://www.bilibili.com/video/av{aid}?p={part_info["page"]}'
+ if first:
+ first = False
+ else:
+ webpage = self._download_webpage(uri, f"{video_id} Part{part_info['page']}")
+ headers = {'referer': uri}
if new_api:
- play_info=re.search(r"window\.__playinfo__=([^<]+)",webpage,re.I) #Get video links from webpage.
- if play_info != None :
- play_info=json.loads(play_info.groups()[0])
- if play_info['code']!=0 :
+ play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I) # Get video links from webpage.
+ if play_info is not None:
+ play_info = json.loads(play_info.groups()[0])
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
- else :
- new_api=False
- play_info=self._download_json(
+ play_info = play_info['data']
+ else:
+ new_api = False
+ play_info = self._download_json(
f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn=120&otype=json&bvid={bvid}&fnver=0&fnval=16",
f"{video_id} Part{part_info['page']}",
"Geting video links.",
"Unable to get video links.")
- if play_info['code']!=0 :
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
- else :
- play_info=self._download_json(
+ play_info = play_info['data']
+ else:
+ play_info = self._download_json(
f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn=120&otype=json&bvid={bvid}&fnver=0&fnval=16",
f"{video_id} Part{part_info['page']}",
"Geting video links.",
"Unable to get video links.")
- if play_info['code']!=0 :
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
- if 'durl' in play_info: # Stream for flv player
- if video_count > 1 and len(play_info['durl']) > 1 and part==None :
+ play_info = play_info['data']
+ if 'durl' in play_info: # Stream for flv player
+ if video_count > 1 and len(play_info['durl']) > 1 and part is None:
self.report_warning(
f"There are multiply FLV files in this part. Please input \"{uri}\" to extract it.",
f"{video_id} Part{part_info['page']}")
continue
- is_durl=True
- if video_count>1:
+ is_durl = True
+ if video_count > 1:
info.update({
- 'title':f"{info['title']} - {part_info['part']}",
- 'id':f"{video_id} P{part_info['page']}"
+ 'title': f"{info['title']} - {part_info['part']}",
+ 'id': f"{video_id} P{part_info['page']}"
})
- video_quality=play_info['quality']
- accept_video_quality_desc=play_info['accept_description']
- accept_video_quality=play_info['accept_quality']
- video_desc_dict={}
- for i in range(len(accept_video_quality)) :
+ video_quality = play_info['quality']
+ accept_video_quality_desc = play_info['accept_description']
+ accept_video_quality = play_info['accept_quality']
+ video_desc_dict = {}
+ for i in range(len(accept_video_quality)):
video_desc_dict.update({
- accept_video_quality[i]:accept_video_quality_desc[i]
+ accept_video_quality[i]: accept_video_quality_desc[i]
})
- video_formats={video_quality:play_info['durl']}
- video_formats_size={video_quality:self._calculate_size(play_info['durl'])} #Total Filesize Dict
- durl_length=[len(play_info['durl'])]
- for video_q in accept_video_quality :
- if video_q not in video_formats :
- if new_api :
- self._set_cookie(domain=".bilibili.com",name="CURRENT_QUALITY",value=f"{video_q}")
- webpage=self._download_webpage(uri,
- f"{video_id} Part{part_info['page']}",
- f"Geting video links for format id : {video_q}.",
- f"Unable to get video links for format id : {video_q}.")
- play_info=re.search(r"window\.__playinfo__=([^<]+)",webpage,re.I) #Get video links from webpage.
- if play_info != None :
- play_info=json.loads(play_info.groups()[0])
- if play_info['code']!=0 :
+ video_formats = {video_quality: play_info['durl']}
+ video_formats_size = {video_quality: self._calculate_size(play_info['durl'])} # Total Filesize Dict
+ durl_length = [len(play_info['durl'])]
+ for video_q in accept_video_quality:
+ if video_q not in video_formats:
+ if new_api:
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value=f"{video_q}")
+ webpage = self._download_webpage(uri,
+ f"{video_id} Part{part_info['page']}",
+ f"Geting video links for format id : {video_q}.",
+ f"Unable to get video links for format id : {video_q}.")
+ play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I) # Get video links from webpage.
+ if play_info is not None:
+ play_info = json.loads(play_info.groups()[0])
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
- else :
- new_api=False
- play_info=self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",f"{video_id} Part{part_info['page']}",
+ play_info = play_info['data']
+ else:
+ new_api = False
+ play_info = self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16", f"{video_id} Part{part_info['page']}",
f"Geting video links for format id : {video_q}.",
f"Unable to get video links for format id : {video_q}.")
- if play_info['code']!=0 :
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
- else :
- play_info=self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",f"{video_id} Part{part_info['page']}",
+ play_info = play_info['data']
+ else:
+ play_info = self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16", f"{video_id} Part{part_info['page']}",
f"Geting video links for format id : {video_q}.",
f"Unable to get video links for format id : {video_q}.")
- if play_info['code']!=0 :
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
- if 'durl' in play_info :
- video_formats[play_info["quality"]]=play_info['durl']
- video_formats_size[play_info["quality"]]=self._calculate_size(play_info['durl'])
+ play_info = play_info['data']
+ if 'durl' in play_info:
+ video_formats[play_info["quality"]] = play_info['durl']
+ video_formats_size[play_info["quality"]] = self._calculate_size(play_info['durl'])
durl_length.append(len(play_info['durl']))
- for i in range(max(durl_length)) :
- entry={}
+ for i in range(max(durl_length)):
+ entry = {}
entry.update(info)
- entry.update({'id':f"{info['id']} Part{i+1}"})
- formats_output=[]
- for video_q in accept_video_quality :
- durl=video_formats[video_q]
- if i < len(durl) :
- video_format=durl[i]
+ entry.update({'id': f"{info['id']} Part{i+1}"})
+ formats_output = []
+ for video_q in accept_video_quality:
+ durl = video_formats[video_q]
+ if i < len(durl):
+ video_format = durl[i]
formats_output.append({
- "url":video_format['url'],
- "format_id":f"{video_q}",
- "ext":"flv",
- "http_headers":headers,
- "filesize":video_format['size']
+ "url": video_format['url'],
+ "format_id": f"{video_q}",
+ "ext": "flv",
+ "http_headers": headers,
+ "filesize": video_format['size']
})
- entry['formats']=formats_output
+ entry['formats'] = formats_output
entries.append(entry)
- elif 'dash' in play_info : # Stream for dash player
- video_quality=play_info['quality']
- accept_video_quality_desc=play_info['accept_description']
- accept_video_quality=play_info['accept_quality']
- accept_audio_quality=[]
- dash=play_info['dash']
- video_quality_list=[]
- video_desc_dict={}
- for i in range(len(accept_video_quality)) :
+ elif 'dash' in play_info: # Stream for dash player
+ video_quality = play_info['quality']
+ accept_video_quality_desc = play_info['accept_description']
+ accept_video_quality = play_info['accept_quality']
+ accept_audio_quality = []
+ dash = play_info['dash']
+ video_quality_list = []
+ video_desc_dict = {}
+ for i in range(len(accept_video_quality)):
video_desc_dict.update({
- accept_video_quality[i]:accept_video_quality_desc[i]
+ accept_video_quality[i]: accept_video_quality_desc[i]
})
- video_formats={}
- for video_format in dash['video'] :
- if video_format['codecs'].startswith('hev') : #Let format id increase 1 to distinguish codec
- video_quality_list.append(video_format['id']+1)
- video_formats[video_format['id']+1]=video_format
- else :
+ video_formats = {}
+ for video_format in dash['video']:
+ if video_format['codecs'].startswith('hev'): # Let format id increase 1 to distinguish codec
+ video_quality_list.append(video_format['id'] + 1)
+ video_formats[video_format['id'] + 1] = video_format
+ else:
video_quality_list.append(video_format['id'])
- video_formats[video_format['id']]=video_format
- bs=True #Try to get all video formats
+ video_formats[video_format['id']] = video_format
+ bs = True # Try to get all video formats
while bs:
- bs=False
- for video_q in accept_video_quality :
+ bs = False
+ for video_q in accept_video_quality:
if video_q not in video_formats:
- if not is_login and video_q <=32 :
- bs=True
- elif is_vip<1 and video_q<=80 and video_q!=74 :
- bs=True
- elif is_vip>0:
- bs=True
- if new_api :
- self._set_cookie(domain=".bilibili.com",name="CURRENT_QUALITY",value=f"{video_q}")
- webpage=self._download_webpage(uri,
- f"{video_id} Part{part_info['page']}",
- f"Geting video links for format id : {video_q}.",
- f"Unable to get video links for format id : {video_q}.")
- play_info=re.search(r"window\.__playinfo__=([^<]+)",webpage,re.I) #Get video links from webpage.
- if play_info != None :
- play_info=json.loads(play_info.groups()[0])
- if play_info['code']!=0 :
+ if not is_login and video_q <= 32:
+ bs = True
+ elif is_vip < 1 and video_q <= 80 and video_q != 74:
+ bs = True
+ elif is_vip > 0:
+ bs = True
+ if new_api:
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value=f"{video_q}")
+ webpage = self._download_webpage(uri,
+ f"{video_id} Part{part_info['page']}",
+ f"Geting video links for format id : {video_q}.",
+ f"Unable to get video links for format id : {video_q}.")
+ play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I) # Get video links from webpage.
+ if play_info is not None:
+ play_info = json.loads(play_info.groups()[0])
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
- else :
- new_api=False
- play_info=self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",f"{video_id} Part{part_info['page']}",
+ play_info = play_info['data']
+ else:
+ new_api = False
+ play_info = self._download_json(
+ f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16", f"{video_id} Part{part_info['page']}",
f"Geting video links for format id : {video_q}.",
f"Unable to get video links for format id : {video_q}.")
- if play_info['code']!=0 :
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
- else :
- play_info=self._download_json(
+ play_info = play_info['data']
+ else:
+ play_info = self._download_json(
f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",
f"{video_id} Part{part_info['page']}",
f"Geting video links for format id : {video_q}.",
f"Unable to get video links for format id : {video_q}.")
- if play_info['code']!=0 :
+ if play_info['code'] != 0:
self._report_error(play_info)
- play_info=play_info['data']
+ play_info = play_info['data']
if 'dash' in play_info:
- for video_format in play_info['dash']['video'] :
- if video_format['codecs'].startswith('hev') : #Let format id increase 1 to distinguish codec
- video_format_q=video_format['id']+1
- else :
- video_format_q=video_format['id']
- if video_format_q not in video_formats :
+ for video_format in play_info['dash']['video']:
+ if video_format['codecs'].startswith('hev'): # Let format id increase 1 to distinguish codec
+ video_format_q = video_format['id'] + 1
+ else:
+ video_format_q = video_format['id']
+ if video_format_q not in video_formats:
video_quality_list.append(video_format_q)
- video_formats[video_format_q]=video_format
- bs=True
+ video_formats[video_format_q] = video_format
+ bs = True
break
- self._set_cookie(domain=".bilibili.com",name="CURRENT_QUALITY",value="120")
- entry={}
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value="120")
+ entry = {}
entry.update(info)
- formats_output=[]
- for i in video_quality_list :
- video_format=video_formats[i]
+ formats_output = []
+ for i in video_quality_list:
+ video_format = video_formats[i]
formats_output.append(
- {"url":video_format['base_url'],
- "ext":"mp4",
- "format_note":video_desc_dict[video_format['id']],
- "format_id":f"{i}",
- "vcodec":video_format['codecs'],
- "fps":self._getfps(video_format['frame_rate']),
- "width":video_format['width'],
- "height":video_format['height'],
- "http_headers":headers
- })
- if 'audio' in dash and dash['audio']!=None :
- for audio_format in dash['audio'] :
+ {"url": video_format['base_url'],
+ "ext": "mp4",
+ "format_note": video_desc_dict[video_format['id']],
+ "format_id": f"{i}",
+ "vcodec": video_format['codecs'],
+ "fps": self._getfps(video_format['frame_rate']),
+ "width": video_format['width'],
+ "height": video_format['height'],
+ "http_headers": headers
+ })
+ if 'audio' in dash and dash['audio'] is not None:
+ for audio_format in dash['audio']:
accept_audio_quality.append(audio_format['id'])
- video_formats[audio_format['id']]=audio_format
+ video_formats[audio_format['id']] = audio_format
accept_audio_quality.sort(reverse=True)
- for audio_quality in accept_audio_quality :
- audio_format=video_formats[audio_quality]
+ for audio_quality in accept_audio_quality:
+ audio_format = video_formats[audio_quality]
formats_output.append({
- "url":audio_format["base_url"],
- "format_id":f"{audio_format['id']}",
- "ext":"mp4",
- "acodec":audio_format['codecs'],
- "http_headers":headers
+ "url": audio_format["base_url"],
+ "format_id": f"{audio_format['id']}",
+ "ext": "mp4",
+ "acodec": audio_format['codecs'],
+ "http_headers": headers
})
- entry.update({"formats":formats_output})
- if video_count > 1 :
- entry.update({"title":f"{info['title']} - {part_info['part']}"})
- entry.update({"id":f"{video_id} P{part_info['page']}"})
+ entry.update({"formats": formats_output})
+ if video_count > 1:
+ entry.update({"title": f"{info['title']} - {part_info['part']}"})
+ entry.update({"id": f"{video_id} P{part_info['page']}"})
entries.append(entry)
- if video_count > 1 :
+ if video_count > 1:
if len(entries) == 1 and not is_durl:
info.update({
- 'formats':entries[0]['formats'],
- 'id':entries[0]['id']
+ 'formats': entries[0]['formats'],
+ 'id': entries[0]['id']
})
return info
info.update({
- "_type":'multi_video',
- "entries":entries
+ "_type": 'multi_video',
+ "entries": entries
})
return info
- else :
+ else:
if not is_durl:
return entries[0]
- else :
- if len(entries)>1 :
+ else:
+ if len(entries) > 1:
info.update({
- "_type":'multi_video',
- "entries":entries
+ "_type": 'multi_video',
+ "entries": entries
})
- else :
+ else:
info.update({
- "formats":entries[0]['formats']
+ "formats": entries[0]['formats']
})
return info
From e53d77b452233d355efaa43316234e1f4e3e6ae8 Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Tue, 4 Aug 2020 17:07:50 +0800
Subject: [PATCH 03/11] remove useless links
---
youtube_dl/extractor/bilibili.py | 14 --------------
1 file changed, 14 deletions(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index e8bcfd099..8db8c8c01 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -47,20 +47,6 @@ class BiliBiliIE(InfoExtractor):
'uploader': '菊子桑',
'uploader_id': '156160',
},
- }, {
- # Tested in BiliBiliBangumiIE
- 'url': 'http://bangumi.bilibili.com/anime/1869/play#40062',
- 'only_matching': True,
- }, {
- 'url': 'http://bangumi.bilibili.com/anime/5802/play#100643',
- 'md5': '3f721ad1e75030cc06faf73587cfec57',
- 'info_dict': {
- 'id': '100643',
- 'ext': 'mp4',
- 'title': 'CHAOS;CHILD',
- 'description': '如果你是神明，并且能够让妄想成为现实。那你会进行怎么样的妄想？是淫靡的世界？独裁社会？毁灭性的制裁？还是……2015年，涩谷。从6年前发生的大灾害“涩谷地震”之后复兴了的这个街区里新设立的私立高中...',
- },
- 'skip': 'Geo-restricted to China',
}, {
# Title with double quotes
'url': 'http://www.bilibili.com/video/av8903802/',
From afbb51d5b094790d6349382aeea49929911d1cc9 Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Tue, 4 Aug 2020 17:10:23 +0800
Subject: [PATCH 04/11] REMOVE Unspport synix in PYTHON2
---
youtube_dl/extractor/bilibili.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 8db8c8c01..2cd26bd70 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -101,7 +101,7 @@ class BiliBiliIE(InfoExtractor):
else:
raise ExtractorError('Can\'t extract Bangumi episode ID')
- def _getfps(self, s: str) -> int:
+ def _getfps(self, s):
"convert fps to int"
if s.isnumeric():
return int(s)
From fa547cfda842df993bb5ce1d2ec7ac025799a09b Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Tue, 4 Aug 2020 17:36:07 +0800
Subject: [PATCH 05/11] REMOVE synax not support(
---
youtube_dl/extractor/bilibili.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 2cd26bd70..f91d7fb56 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -113,7 +113,7 @@ class BiliBiliIE(InfoExtractor):
else:
return 0
- def _calculate_size(self, durl: list) -> int:
+ def _calculate_size(self, durl):
"Calculate total file size."
s = 0
for i in durl:
From 96cb93d771490e1311b0bc9e257a1e3cadaa1ecf Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Tue, 4 Aug 2020 18:27:25 +0800
Subject: [PATCH 06/11] change string format method
---
youtube_dl/extractor/bilibili.py | 81 +++++++++++++++++---------------
1 file changed, 42 insertions(+), 39 deletions(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index f91d7fb56..805d7d433 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -151,7 +151,7 @@ class BiliBiliIE(InfoExtractor):
video_count = video_data['videos']
tags_info = self._download_json(
- f"https://api.bilibili.com/x/web-interface/view/detail/tag?aid={aid}", video_id,
+ "https://api.bilibili.com/x/web-interface/view/detail/tag?aid=%s" % (aid), video_id,
'Geting video tags.', 'Unable to get Login/User Information.')
if tags_info['code'] != 0:
self._report_error(tags_info)
@@ -181,7 +181,7 @@ class BiliBiliIE(InfoExtractor):
'uploader': uploader_data['name'],
'uploader_id': uploader_data['mid'],
'duration': video_data['duration'],
- 'webpage_url': f'https://www.bilibili.com/video/av{aid}',
+ 'webpage_url': 'https://www.bilibili.com/video/av%s' % (aid),
'categories': [video_data['tname']],
'view_count': video_data['stat']['viewseo'],
'comment_count': video_data['stat']['reply'],
@@ -198,11 +198,11 @@ class BiliBiliIE(InfoExtractor):
for part_info in video_data['pages']:
if part is not None and part_info["page"] != part:
continue
- uri = f'https://www.bilibili.com/video/av{aid}?p={part_info["page"]}'
+ uri = 'https://www.bilibili.com/video/av%s?p=%s' % (aid, part_info["page"])
if first:
first = False
else:
- webpage = self._download_webpage(uri, f"{video_id} Part{part_info['page']}")
+ webpage = self._download_webpage(uri, "%s Part%s" % (video_id, part_info['page']))
headers = {'referer': uri}
if new_api:
play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I) # Get video links from webpage.
@@ -214,8 +214,8 @@ class BiliBiliIE(InfoExtractor):
else:
new_api = False
play_info = self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn=120&otype=json&bvid={bvid}&fnver=0&fnval=16",
- f"{video_id} Part{part_info['page']}",
+ "https://api.bilibili.com/x/player/playurl?cid=%s&qn=120&otype=json&bvid=%s&fnver=0&fnval=16" % (part_info['cid'], bvid),
+ "%s Part%s" % (video_id, part_info['page']),
"Geting video links.",
"Unable to get video links.")
if play_info['code'] != 0:
@@ -223,8 +223,8 @@ class BiliBiliIE(InfoExtractor):
play_info = play_info['data']
else:
play_info = self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn=120&otype=json&bvid={bvid}&fnver=0&fnval=16",
- f"{video_id} Part{part_info['page']}",
+ "https://api.bilibili.com/x/player/playurl?cid=%s&qn=120&otype=json&bvid=%s&fnver=0&fnval=16" % (part_info['cid'], bvid),
+ "%s Part%s" % (video_id, part_info['page']),
"Geting video links.",
"Unable to get video links.")
if play_info['code'] != 0:
@@ -233,14 +233,14 @@ class BiliBiliIE(InfoExtractor):
if 'durl' in play_info: # Stream for flv player
if video_count > 1 and len(play_info['durl']) > 1 and part is None:
self.report_warning(
- f"There are multiply FLV files in this part. Please input \"{uri}\" to extract it.",
- f"{video_id} Part{part_info['page']}")
+ "There are multiply FLV files in this part. Please input \"%s\" to extract it." % (uri),
+ "%s Part%s" % (video_id, part_info['page']))
continue
is_durl = True
if video_count > 1:
info.update({
- 'title': f"{info['title']} - {part_info['part']}",
- 'id': f"{video_id} P{part_info['page']}"
+ 'title': "%s - %s" % (info['title'], part_info['part']),
+ 'id': "%s P%s" % (video_id, part_info['page'])
})
video_quality = play_info['quality']
accept_video_quality_desc = play_info['accept_description']
@@ -256,11 +256,11 @@ class BiliBiliIE(InfoExtractor):
for video_q in accept_video_quality:
if video_q not in video_formats:
if new_api:
- self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value=f"{video_q}")
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value=str(video_q))
webpage = self._download_webpage(uri,
- f"{video_id} Part{part_info['page']}",
- f"Geting video links for format id : {video_q}.",
- f"Unable to get video links for format id : {video_q}.")
+ "%s Part%s" % (video_id, part_info['page']),
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q))
play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I) # Get video links from webpage.
if play_info is not None:
play_info = json.loads(play_info.groups()[0])
@@ -270,17 +270,19 @@ class BiliBiliIE(InfoExtractor):
else:
new_api = False
play_info = self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16", f"{video_id} Part{part_info['page']}",
- f"Geting video links for format id : {video_q}.",
- f"Unable to get video links for format id : {video_q}.")
+ "https://api.bilibili.com/x/player/playurl?cid=%s&qn=%s&otype=json&bvid=%s&fnver=0&fnval=16" % (part_info['cid'], video_q, bvid),
+ "%s Part%s" % (video_id, part_info['page']),
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q))
if play_info['code'] != 0:
self._report_error(play_info)
play_info = play_info['data']
else:
play_info = self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16", f"{video_id} Part{part_info['page']}",
- f"Geting video links for format id : {video_q}.",
- f"Unable to get video links for format id : {video_q}.")
+ "https://api.bilibili.com/x/player/playurl?cid=%s&qn=%s&otype=json&bvid=%s&fnver=0&fnval=16" % (part_info['cid'], video_q, bvid),
+ "%s Part%s" % (video_id, part_info['page']),
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q))
if play_info['code'] != 0:
self._report_error(play_info)
play_info = play_info['data']
@@ -291,7 +293,7 @@ class BiliBiliIE(InfoExtractor):
for i in range(max(durl_length)):
entry = {}
entry.update(info)
- entry.update({'id': f"{info['id']} Part{i+1}"})
+ entry.update({'id': "%s Part%s" % (info['id'], i + 1)})
formats_output = []
for video_q in accept_video_quality:
durl = video_formats[video_q]
@@ -299,7 +301,7 @@ class BiliBiliIE(InfoExtractor):
video_format = durl[i]
formats_output.append({
"url": video_format['url'],
- "format_id": f"{video_q}",
+ "format_id": str(video_q),
"ext": "flv",
"http_headers": headers,
"filesize": video_format['size']
@@ -338,11 +340,11 @@ class BiliBiliIE(InfoExtractor):
elif is_vip > 0:
bs = True
if new_api:
- self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value=f"{video_q}")
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value=str(video_q))
webpage = self._download_webpage(uri,
- f"{video_id} Part{part_info['page']}",
- f"Geting video links for format id : {video_q}.",
- f"Unable to get video links for format id : {video_q}.")
+ "%s Part%s" % (video_id, part_info['page']),
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q))
play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I) # Get video links from webpage.
if play_info is not None:
play_info = json.loads(play_info.groups()[0])
@@ -352,18 +354,19 @@ class BiliBiliIE(InfoExtractor):
else:
new_api = False
play_info = self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16", f"{video_id} Part{part_info['page']}",
- f"Geting video links for format id : {video_q}.",
- f"Unable to get video links for format id : {video_q}.")
+ "https://api.bilibili.com/x/player/playurl?cid=%s&qn=%s&otype=json&bvid=%s&fnver=0&fnval=16" % (part_info['cid'], video_q, bvid),
+ "%s Part%s" % (video_id, part_info['page']),
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q))
if play_info['code'] != 0:
self._report_error(play_info)
play_info = play_info['data']
else:
play_info = self._download_json(
- f"https://api.bilibili.com/x/player/playurl?cid={part_info['cid']}&qn={video_q}&otype=json&bvid={bvid}&fnver=0&fnval=16",
- f"{video_id} Part{part_info['page']}",
- f"Geting video links for format id : {video_q}.",
- f"Unable to get video links for format id : {video_q}.")
+ "https://api.bilibili.com/x/player/playurl?cid=%s&qn=%s&otype=json&bvid=%s&fnver=0&fnval=16" % (part_info['cid'], video_q, bvid),
+ "%s Part%s" % (video_id, part_info['page']),
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q))
if play_info['code'] != 0:
self._report_error(play_info)
play_info = play_info['data']
@@ -388,7 +391,7 @@ class BiliBiliIE(InfoExtractor):
{"url": video_format['base_url'],
"ext": "mp4",
"format_note": video_desc_dict[video_format['id']],
- "format_id": f"{i}",
+ "format_id": str(i),
"vcodec": video_format['codecs'],
"fps": self._getfps(video_format['frame_rate']),
"width": video_format['width'],
@@ -404,15 +407,15 @@ class BiliBiliIE(InfoExtractor):
audio_format = video_formats[audio_quality]
formats_output.append({
"url": audio_format["base_url"],
- "format_id": f"{audio_format['id']}",
+ "format_id": str(audio_format['id']),
"ext": "mp4",
"acodec": audio_format['codecs'],
"http_headers": headers
})
entry.update({"formats": formats_output})
if video_count > 1:
- entry.update({"title": f"{info['title']} - {part_info['part']}"})
- entry.update({"id": f"{video_id} P{part_info['page']}"})
+ entry.update({"title": "%s - %s" % (info['title'], part_info['part'])})
+ entry.update({"id": "%s P%s" % (video_id, part_info['page'])})
entries.append(entry)
if video_count > 1:
From 6532b27c71af7a51e75f46a32e473ad597cea2fe Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Tue, 4 Aug 2020 18:37:29 +0800
Subject: [PATCH 07/11] display format_note when extractor dash streams
---
youtube_dl/extractor/bilibili.py | 1 +
1 file changed, 1 insertion(+)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 805d7d433..d9f362a74 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -302,6 +302,7 @@ class BiliBiliIE(InfoExtractor):
formats_output.append({
"url": video_format['url'],
"format_id": str(video_q),
+ "format_note": video_desc_dict[video_q],
"ext": "flv",
"http_headers": headers,
"filesize": video_format['size']
From ac144ed961010e19f718539767c58593e2027a9f Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Wed, 5 Aug 2020 06:21:38 +0800
Subject: [PATCH 08/11] fix typo and small bugs in code.
---
youtube_dl/extractor/bilibili.py | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index d9f362a74..c64013753 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -152,7 +152,7 @@ class BiliBiliIE(InfoExtractor):
tags_info = self._download_json(
"https://api.bilibili.com/x/web-interface/view/detail/tag?aid=%s" % (aid), video_id,
- 'Geting video tags.', 'Unable to get Login/User Information.')
+ 'Geting video tags.', 'Unable to get video tags.')
if tags_info['code'] != 0:
self._report_error(tags_info)
tags_info = tags_info['data']
@@ -290,6 +290,7 @@ class BiliBiliIE(InfoExtractor):
video_formats[play_info["quality"]] = play_info['durl']
video_formats_size[play_info["quality"]] = self._calculate_size(play_info['durl'])
durl_length.append(len(play_info['durl']))
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value="120")
for i in range(max(durl_length)):
entry = {}
entry.update(info)
From 6b8d4e09c126bd4bd5a471a7fb7141523ee27c6d Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Wed, 5 Aug 2020 14:56:02 +0800
Subject: [PATCH 09/11] Support to extract bangumi
---
youtube_dl/extractor/bilibili.py | 478 +++++++++++++++++++++++++++----
1 file changed, 426 insertions(+), 52 deletions(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index c64013753..bd379cc20 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -449,70 +449,444 @@ class BiliBiliIE(InfoExtractor):
class BiliBiliBangumiIE(InfoExtractor):
- _VALID_URL = r'https?://bangumi\.bilibili\.com/anime/(?P<id>\d+)'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:(?:www)\.)?
+ bilibili\.(?:tv|com)/
+ (?:
+ (?:
+ bangumi/play/[sS][sS]
+ )(?P<ssid>\d+)|
+ bangumi/play/[eE][pP](?P<epid>\d+)
+ )
+ '''
- IE_NAME = 'bangumi.bilibili.com'
+ IE_NAME = 'bilibili bangumi'
IE_DESC = 'BiliBili番剧'
- _TESTS = [{
- 'url': 'http://bangumi.bilibili.com/anime/1869',
- 'info_dict': {
- 'id': '1869',
- 'title': '混沌武士',
- 'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
- },
- 'playlist_count': 26,
- }, {
- 'url': 'http://bangumi.bilibili.com/anime/1869',
- 'info_dict': {
- 'id': '1869',
- 'title': '混沌武士',
- 'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
- },
- 'playlist': [{
- 'md5': '91da8621454dd58316851c27c68b0c13',
- 'info_dict': {
- 'id': '40062',
- 'ext': 'mp4',
- 'title': '混沌武士',
- 'description': '故事发生在日本的江户时代。风是一个小酒馆的打工女。一日，酒馆里来了一群恶霸，虽然他们的举动令风十分不满，但是毕竟风只是一届女流，无法对他们采取什么行动，只能在心里嘟哝。这时，酒家里又进来了个“不良份子...',
- 'timestamp': 1414538739,
- 'upload_date': '20141028',
- 'episode': '疾风怒涛 Tempestuous Temperaments',
- 'episode_number': 1,
- },
- }],
- 'params': {
- 'playlist_items': '1',
- },
- }]
+ _TESTS = []
- @classmethod
+ @ classmethod
def suitable(cls, url):
return False if BiliBiliIE.suitable(url) else super(BiliBiliBangumiIE, cls).suitable(url)
+ def _get_episode_list(self, bangumi_info):
+ ep_list = bangumi_info['epList']
+ episode_list = []
+ for i in ep_list:
+ temp = {}
+ temp.update(i)
+ episode_list.append(temp)
+ if 'sections' in bangumi_info:
+ for section in bangumi_info['sections']:
+ for i in section['epList']:
+ temp = {}
+ temp.update(i)
+ temp.update({
+ "section_title": section['title'],
+ "section_id": section['id']
+ })
+ episode_list.append(temp)
+ return episode_list
+
+ def _report_error(self, error):
+ if 'message' in error:
+ raise ExtractorError(error['message'])
+ elif 'code' in error:
+ raise ExtractorError(str(error['code']))
+ else:
+ raise ExtractorError(str(error))
+
+ def _report_warning(self, warning, video_id=None):
+ if 'message' in warning:
+ self.report_warning(warning['message'], video_id)
+ elif 'code' in warning:
+ self.report_warning(str(warning['code']), video_id)
+ else:
+ self.report_warning(str(warning), video_id)
+
+ def _calculate_size(self, durl):
+ "Calculate total file size."
+ s = 0
+ for i in durl:
+ s = s + i['size']
+ return s
+
+ def _getfps(self, s):
+ "convert fps to int"
+ if s.isnumeric():
+ return int(s)
+ else:
+ r = re.search(r"([0-9]+)/([0-9]+)", s)
+ if r is not None:
+ r = r.groups()
+ return int(r[0]) / int(r[1])
+ else:
+ return 0
+
+ def _extract_episode(self, episode_info):
+ epid = episode_info['id']
+ uri = "https://www.bilibili.com/bangumi/play/ep%s" % (epid)
+ if self._epid is None:
+ video_id = "%s %s" % (self._video_id, episode_info['titleFormat'])
+ if self._first:
+ webpage = self._webpage
+ self._first = False
+ else:
+ webpage = self._download_webpage(uri, video_id)
+ headers = {'referer': uri}
+ if self._new_api:
+ play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I)
+ if play_info is not None:
+ play_info = json.loads(play_info.groups()[0])
+ if play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['data']
+ else:
+ self._new_api = False
+ play_info = self._download_json(
+ "https://api.bilibili.com/pgc/player/web/playurl?cid=%s&qn=120&type=&otype=json&fourk=1&bvid=%s&ep_id=%s&fnver=0&fnval=16&session=" % (episode_info['cid'], episode_info['bvid'], epid),
+ video_id,
+ "Geting video links.",
+ "Unable to get video links.",
+ headers=headers)
+ if play_info['code'] == -10403: # Need vip or buy
+ self._new_api = True
+ self._report_warning(play_info)
+ elif play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['result']
+ else:
+ play_info = self._download_json(
+ "https://api.bilibili.com/pgc/player/web/playurl?cid=%s&qn=120&type=&otype=json&fourk=1&bvid=%s&ep_id=%s&fnver=0&fnval=16&session=" % (episode_info['cid'], episode_info['bvid'], epid),
+ video_id,
+ "Geting video links.",
+ "Unable to get video links.",
+ headers=headers)
+ if play_info['code'] == -10403: # Need vip or buy
+ self._report_warning(play_info)
+ elif play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['result']
+ if 'durl' in play_info: # Stream for flv player
+ if self._video_count > 1 and len(play_info['durl']) > 1 and self._epid is None:
+ self._report_warning(
+ "There are multiply FLV files in this episode. Please input \"%s\" to extract it." % (uri),
+ video_id)
+ return
+ self._is_durl = True
+ if self._epid is not None:
+ self._info.update({
+ "title": "%s - %s %s" % (self._info['title'], episode_info['titleFormat'], episode_info['longTitle']),
+ "id": video_id,
+ "episode": episode_info['longTitle'],
+ "episode_id": episode_info['id']
+ })
+ video_quality = play_info['quality']
+ accept_video_quality_desc = play_info['accept_description']
+ accept_video_quality = play_info['accept_quality']
+ video_desc_dict = {}
+ for i in range(len(accept_video_quality)):
+ video_desc_dict.update({
+ accept_video_quality[i]: accept_video_quality_desc[i]
+ })
+ video_formats = {video_quality: play_info['durl']}
+ video_formats_size = {video_quality: self._calculate_size(play_info['durl'])}
+ durl_length = [len(play_info['durl'])]
+ for video_q in accept_video_quality:
+ if video_q not in video_formats:
+ if self._new_api:
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value=str(video_q))
+ webpage = self._download_webpage(
+ uri,
+ video_id,
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q))
+ play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I)
+ if play_info is not None:
+ play_info = json.loads(play_info.groups()[0])
+ if play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['data']
+ else:
+ self._new_api = False
+ play_info = self._download_json(
+ "https://api.bilibili.com/pgc/player/web/playurl?cid=%s&qn=%s&type=&otype=json&fourk=1&bvid=%s&ep_id=%s&fnver=0&fnval=16&session=" % (episode_info['cid'], video_q, episode_info['bvid'], epid),
+ video_id,
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q),
+ headers=headers)
+ if play_info['code'] == -10403: # Need vip or buy
+ self._new_api = True
+ self._report_warning(play_info)
+ elif play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['result']
+ else:
+ play_info = self._download_json(
+ "https://api.bilibili.com/pgc/player/web/playurl?cid=%s&qn=%s&type=&otype=json&fourk=1&bvid=%s&ep_id=%s&fnver=0&fnval=16&session=" % (episode_info['cid'], video_q, episode_info['bvid'], epid),
+ video_id,
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q),
+ headers=headers)
+ if play_info['code'] == -10403: # Need vip or buy
+ self._report_warning(play_info)
+ elif play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['result']
+ if 'durl' in play_info:
+ video_formats[play_info["quality"]] = play_info['durl']
+ video_formats_size[play_info["quality"]] = self._calculate_size(play_info['durl'])
+ durl_length.append(len(play_info['durl']))
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value="120")
+ for i in range(max(durl_length)):
+ entry = {}
+ entry.update(self._info)
+ if self._epid is None:
+ entry.update({
+ "title": "%s - %s %s" % (self._info['title'], episode_info['titleFormat'], episode_info['longTitle']),
+ "id": video_id,
+ "episode": episode_info['longTitle'],
+ "episode_id": episode_info['id']
+ })
+ else:
+ entry.update({
+ "id": "%s Part%s" % (video_id, i + 1)
+ })
+ formats_output = []
+ for video_q in accept_video_quality:
+ durl = video_formats[video_q]
+ if i < len(durl):
+ video_format = durl[i]
+ formats_output.append({
+ "url": video_format['url'],
+ "format_id": str(video_q),
+ "format_note": video_desc_dict[video_q],
+ "ext": "flv",
+ "http_headers": headers,
+ "filesize": video_format['size']
+ })
+ entry['formats'] = formats_output
+ self._entries.append(entry)
+ elif 'dash' in play_info: # Stream for dash player
+ video_quality = play_info['quality']
+ accept_video_quality_desc = play_info['accept_description']
+ accept_video_quality = play_info['accept_quality']
+ accept_audio_quality = []
+ dash = play_info['dash']
+ video_quality_list = []
+ video_desc_dict = {}
+ for i in range(len(accept_video_quality)):
+ video_desc_dict.update({
+ accept_video_quality[i]: accept_video_quality_desc[i]
+ })
+ video_formats = {}
+ for video_format in dash['video']:
+ if video_format['codecs'].startswith('hev'):
+ video_quality_list.append(video_format['id'] + 1)
+ video_formats[video_format['id'] + 1] = video_format
+ else:
+ video_quality_list.append(video_format['id'])
+ video_formats[video_format['id']] = video_format
+ bs = True # Try to get all video formats
+ while bs:
+ bs = False
+ for video_q in accept_video_quality:
+ if video_q not in video_formats:
+ if not self._is_login and video_q <= 32:
+ bs = True
+ elif self._is_vip < 1 and video_q <= 80 and video_q != 74:
+ bs = True
+ elif self._is_vip > 0:
+ bs = True
+ if self._new_api:
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value=str(video_q))
+ webpage = self._download_webpage(
+ uri,
+ video_id,
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q))
+ play_info = re.search(r"window\.__playinfo__=([^<]+)", webpage, re.I)
+ if play_info is not None:
+ play_info = json.loads(play_info.groups()[0])
+ if play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['data']
+ else:
+ self._new_api = False
+ play_info = self._download_json(
+ "https://api.bilibili.com/pgc/player/web/playurl?cid=%s&qn=%s&type=&otype=json&fourk=1&bvid=%s&ep_id=%s&fnver=0&fnval=16&session=" % (episode_info['cid'], video_q, episode_info['bvid'], epid),
+ video_id,
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q),
+ headers=headers)
+ if play_info['code'] == -10403: # Need vip or buy
+ self._new_api = True
+ self._report_warning(play_info)
+ elif play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['result']
+ else:
+ play_info = self._download_json(
+ "https://api.bilibili.com/pgc/player/web/playurl?cid=%s&qn=%s&type=&otype=json&fourk=1&bvid=%s&ep_id=%s&fnver=0&fnval=16&session=" % (episode_info['cid'], video_q, episode_info['bvid'], epid),
+ video_id,
+ "Geting video links for format id : %s." % (video_q),
+ "Unable to get video links for format id : %s." % (video_q),
+ headers=headers)
+ if play_info['code'] == -10403: # Need vip or buy
+ self._report_warning(play_info)
+ elif play_info['code'] != 0:
+ self._report_error(play_info)
+ play_info = play_info['result']
+ if 'dash' in play_info:
+ for video_format in play_info['dash']['video']:
+ if video_format['codecs'].startswith('hev'): # Let format id increase 1 to distinguish codec
+ video_format_q = video_format['id'] + 1
+ else:
+ video_format_q = video_format['id']
+ if video_format_q not in video_formats:
+ video_quality_list.append(video_format_q)
+ video_formats[video_format_q] = video_format
+ bs = True
+ break
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value="120")
+ entry = {}
+ entry.update(self._info)
+ entry.update({
+ "title": "%s - %s %s" % (self._info['title'], episode_info['titleFormat'], episode_info['longTitle']),
+ "id": video_id,
+ "episode": episode_info['longTitle'],
+ "episode_id": episode_info['id']
+ })
+ formats_output = []
+ for i in video_quality_list:
+ video_format = video_formats[i]
+ formats_output.append({
+ "url": video_format['base_url'],
+ "ext": "mp4",
+ "format_note": video_desc_dict[video_format['id']],
+ "format_id": str(i),
+ "vcodec": video_format['codecs'],
+ "fps": self._getfps(video_format['frame_rate']),
+ "width": video_format['width'],
+ "height": video_format['height'],
+ "http_headers": headers
+ })
+ if 'audio' in dash and dash['audio'] is not None:
+ for audio_format in dash['audio']:
+ accept_audio_quality.append(audio_format['id'])
+ video_formats[audio_format['id']] = audio_format
+ accept_audio_quality.sort(reverse=True)
+ for audio_quality in accept_audio_quality:
+ audio_format = video_formats[audio_quality]
+ formats_output.append({
+ "url": audio_format["base_url"],
+ "format_id": str(audio_format['id']),
+ "ext": "mp4",
+ "acodec": audio_format['codecs'],
+ "http_headers": headers
+ })
+ entry.update({"formats": formats_output})
+ self._entries.append(entry)
+
def _real_extract(self, url):
- bangumi_id = self._match_id(url)
+ url, smuggled_data = unsmuggle_url(url, {})
- # Sometimes this API returns a JSONP response
- season_info = self._download_json(
- 'http://bangumi.bilibili.com/jsonp/seasoninfo/%s.ver' % bangumi_id,
- bangumi_id, transform_source=strip_jsonp)['result']
+ mobj = re.match(self._VALID_URL, url)
+ ssid = mobj.group('ssid')
+ epid = mobj.group('epid')
+ video_id = ssid or epid
+ if ssid is not None:
+ ssid = int(ssid)
+ video_id = "ss" + video_id
+ if epid is not None:
+ epid = int(epid)
+ video_id = "ep" + video_id
- entries = [{
- '_type': 'url_transparent',
- 'url': smuggle_url(episode['webplay_url'], {'no_bangumi_tip': 1}),
- 'ie_key': BiliBiliIE.ie_key(),
- 'timestamp': parse_iso8601(episode.get('update_time'), delimiter=' '),
- 'episode': episode.get('index_title'),
- 'episode_number': int_or_none(episode.get('index')),
- } for episode in season_info['episodes']]
+ # Set Cookies need to parse the Links.
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_QUALITY", value="120") # Set default video quality
+ self._set_cookie(domain=".bilibili.com", name="CURRENT_FNVAL", value="16")
+ self._set_cookie(domain=".bilibili.com", name="laboratory", value="1-1") # Use new webpage API
+ self._set_cookie(domain=".bilibili.com", name="stardustvideo", value="1")
- entries = sorted(entries, key=lambda entry: entry.get('episode_number'))
+ webpage = self._download_webpage(url, video_id)
- return self.playlist_result(
- entries, bangumi_id,
- season_info.get('bangumi_title'), season_info.get('evaluate'))
+ bangumi_info = re.search(r"window\.__INITIAL_STATE__=([^;]+)", webpage, re.I)
+ if bangumi_info is not None:
+ bangumi_info = json.loads(bangumi_info.groups()[0])
+ else:
+ raise ExtractorError("Can not find the bangumi.")
+ media_info = bangumi_info['mediaInfo']
+ if ssid is None:
+ ssid = int(media_info['ssId'])
+
+ user_info = self._download_json(
+ "https://api.bilibili.com/x/web-interface/nav", video_id,
+ "Geting Login/User Information.", "Unable to get Login/User Information.")
+ if user_info['code'] != 0 and user_info['code'] != -101:
+ self._report_error(user_info)
+ user_info = user_info['data']
+ self._is_login = user_info['isLogin']
+ if self._is_login:
+ self._is_vip = user_info['vipStatus']
+ else:
+ self._is_vip = 0
+ self._is_durl = False # If return the durl Stream, this will be true
+
+ self._info = {
+ "series": media_info['series'],
+ "title": media_info['title'],
+ "season": media_info['title'],
+ "season_id": media_info['ssId'],
+ "id": video_id,
+ "thumbnail": "https:" + media_info['cover'],
+ "description": media_info['evaluate'],
+ "uploader": media_info['upInfo']['name'],
+ "release_date": media_info['pub']['time'][0:4] + media_info['pub']['time'][5:7] + media_info['pub']['time'][8:10],
+ "uploader_id": media_info['upInfo']['mid'],
+ "view_count": media_info['stat']['views'],
+ "like_count": media_info['stat']['favorites'],
+ "comment_count": media_info['stat']['reply'],
+ "webpage_url": "https://www.bilibili.com/bangumi/play/%s" % (video_id)
+ }
+
+ ep_list = self._get_episode_list(bangumi_info)
+ if epid is not None:
+ ep_info = None
+ for ep in ep_list:
+ if ep['id'] == epid:
+ ep_info = ep
+ break
+ if ep_info is None:
+ self._report_error("Can not find the infomation of ep%s." % (epid))
+ self._video_count = len(ep_list)
+ self._new_api = True # Parse video links from webpage first.
+ self._first = True # First Part
+ self._webpage = webpage
+ self._video_id = video_id
+ self._epid = epid
+ self._entries = []
+ if epid is not None:
+ self._extract_episode(ep_info)
+ else:
+ for ep_info in ep_list:
+ self._extract_episode(ep_info)
+
+ if epid is None:
+ self._info.update({
+ "_type": 'multi_video',
+ 'entries': self._entries
+ })
+ return self._info
+ else:
+ if len(self._entries) == 1:
+ return self._entries[0]
+ else:
+ self._info.update({
+ "_type": 'multi_video',
+ 'entries': self._entries
+ })
+ return self._info
class BilibiliAudioBaseIE(InfoExtractor):
From ca4d8aeab31f1257e228bc1f12b3f491703291e8 Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Wed, 5 Aug 2020 15:02:33 +0800
Subject: [PATCH 10/11] remove not use import
---
youtube_dl/extractor/bilibili.py | 3 ---
1 file changed, 3 deletions(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index bd379cc20..68f95be7f 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -11,10 +11,7 @@ from ..compat import (
from ..utils import (
ExtractorError,
int_or_none,
- parse_iso8601,
- smuggle_url,
str_or_none,
- strip_jsonp,
unsmuggle_url,
)
From 650850772504835f54e9dcb8cb1f13703e4955ba Mon Sep 17 00:00:00 2001
From: lifegpc <g1710431395@gmail.com>
Date: Wed, 5 Aug 2020 17:35:40 +0800
Subject: [PATCH 11/11] Complete redirect to Bangumi episode ID. Fix bug
---
youtube_dl/extractor/bilibili.py | 18 ++++++++++++++++--
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 68f95be7f..6f774999c 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -139,8 +139,20 @@ class BiliBiliIE(InfoExtractor):
if video_info is not None:
video_info = json.loads(video_info.groups()[0])
else:
- self._report_error("") # TODO Should redirect to Bangumi episode ID.
- # https://api.bilibili.com/x/web-interface/view/detail?bvid=&aid=&jsonp=jsonp have redirect links.
+ if mobj.group('id') is not None:
+ uri = "https://api.bilibili.com/x/web-interface/view/detail?bvid=BV%s&aid=&jsonp=jsonp" % (video_id)
+ else:
+ uri = "https://api.bilibili.com/x/web-interface/view/detail?bvid=&aid=%s&jsonp=jsonp" % (video_id)
+ redriect_info = self._download_json(
+ uri, video_id,
+ "Geting redriect information.", "Unable to get redriect information.")
+ if redriect_info['code'] != 0:
+ self._report_error(redriect_info)
+ redriect_info = redriect_info['data']
+ if 'View' in redriect_info and 'redirect_url' in redriect_info['View']:
+ return self.url_result(redriect_info['View']['redirect_url'])
+ else:
+ raise ExtractorError("Can not find redirect URL.")
video_data = video_info['videoData']
uploader_data = video_info['upData']
aid = video_data['aid']
@@ -526,6 +538,8 @@ class BiliBiliBangumiIE(InfoExtractor):
uri = "https://www.bilibili.com/bangumi/play/ep%s" % (epid)
if self._epid is None:
video_id = "%s %s" % (self._video_id, episode_info['titleFormat'])
+ else:
+ video_id = self._video_id
if self._first:
webpage = self._webpage
self._first = False