w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[twitcasting] Improve extraction and fix issues (closes #17981)

Browse source
This commit is contained in:
Sergey M․ 2018-11-03 00:27:36 +07:00
parent 036f905161
commit cf0db4d997
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 27 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
youtube_dl/extractor/extractors.py
View file

@ -1196,7 +1196,7 @@ from .tweakers import TweakersIE
from .twentyfourvideo import TwentyFourVideoIE from .twentyfourvideo import TwentyFourVideoIE
from .twentymin import TwentyMinutenIE from .twentymin import TwentyMinutenIE
from .twentythreevideo import TwentyThreeVideoIE from .twentythreevideo import TwentyThreeVideoIE
from .twitcasting import TwitcastingIE from .twitcasting import TwitCastingIE
from .twitch import ( from .twitch import (
TwitchVideoIE, TwitchVideoIE,
TwitchChapterIE, TwitchChapterIE,

36
youtube_dl/extractor/twitcasting.py
View file

@ -6,8 +6,8 @@ from .common import InfoExtractor
import re import re
class TwitcastingIE(InfoExtractor): class TwitCastingIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|ssl|en|pt|es|ja|ko)\.)?twitcasting\.tv/(?P<uploader_id>[^\/]+)/movie/(?P<video_id>[0-9]+)' _VALID_URL = r'https?://(?:[^/]+\.)?twitcasting\.tv/(?P<uploader_id>[^/]+)/movie/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'https://twitcasting.tv/ivetesangalo/movie/2357609', 'url': 'https://twitcasting.tv/ivetesangalo/movie/2357609',
'md5': '745243cad58c4681dc752490f7540d7f', 'md5': '745243cad58c4681dc752490f7540d7f',
@ -18,24 +18,40 @@ class TwitcastingIE(InfoExtractor):
'uploader_id': 'ivetesangalo', 'uploader_id': 'ivetesangalo',
'description': "Moi! I'm live on TwitCasting from my iPhone.", 'description': "Moi! I'm live on TwitCasting from my iPhone.",
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
} },
'params': {
'skip_download': True,
},
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id') video_id = mobj.group('id')
uploader_id = mobj.group('uploader_id') uploader_id = mobj.group('uploader_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
playlist_url = self._html_search_regex(r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage, name='playlist url', group='url') title = self._html_search_regex(
formats = self._extract_m3u8_formats(playlist_url, video_id, ext='mp4') r'(?s)<[^>]+id=["\']movietitle[^>]+>(.+?)</',
webpage, 'title', default=None) or self._html_search_meta(
'twitter:title', webpage, fatal=True)
m3u8_url = self._search_regex(
(r'data-movie-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
r'(["\'])(?P<url>http.+?\.m3u8.*?)\1'),
webpage, 'm3u8 url', group='url')
formats = self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
title = self._html_search_meta('twitter:title', webpage) description = self._og_search_description(
description = self._og_search_description(webpage) or self._html_search_meta('twitter:description', webpage) webpage, default=None) or self._html_search_meta(
return{ 'twitter:description', webpage)
return {
'id': video_id, 'id': video_id,
'url': url,
'title': title, 'title': title,
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,