[20min] Improve
This commit is contained in:
Sergey M․
@@ -4,116 +4,88 @@ from __future__ import unicode_literals
|
|||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import remove_end
|
from ..utils import (
|
||||||
|
int_or_none,
|
||||||
|
try_get,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
class TwentyMinutenIE(InfoExtractor):
|
class TwentyMinutenIE(InfoExtractor):
|
||||||
IE_NAME = '20min'
|
IE_NAME = '20min'
|
||||||
_VALID_URL = r'https?://(?:www\.)?20min\.ch/(?:videotv/*\?.*\bvid=(?P<id>\d+)|(?:[^/]+/)*(?P<display_id>[^/#?]+))'
|
_VALID_URL = r'''(?x)
|
||||||
|
https?://
|
||||||
|
(?:www\.)?20min\.ch/
|
||||||
|
(?:
|
||||||
|
videotv/*\?.*?\bvid=|
|
||||||
|
videoplayer/videoplayer\.html\?.*?\bvideoId@
|
||||||
|
)
|
||||||
|
(?P<id>\d+)
|
||||||
|
'''
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
# regular video
|
|
||||||
'url': 'http://www.20min.ch/videotv/?vid=469148&cid=2',
|
'url': 'http://www.20min.ch/videotv/?vid=469148&cid=2',
|
||||||
'md5': 'e7264320db31eed8c38364150c12496e',
|
'md5': 'e7264320db31eed8c38364150c12496e',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '469148',
|
'id': '469148',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '85 000 Franken für 15 perfekte Minuten',
|
'title': '85 000 Franken für 15 perfekte Minuten',
|
||||||
'description': 'Was die Besucher vom Silvesterzauber erwarten können. (Video: Alice Grosjean/Murat Temel)',
|
'thumbnail': r're:https?://.*\.jpg$',
|
||||||
'thumbnail': 'http://thumbnails.20min-tv.ch/server063/469148/frame-72-469148.jpg'
|
|
||||||
}
|
|
||||||
}, {
|
|
||||||
# news article with video
|
|
||||||
'url': 'http://www.20min.ch/schweiz/news/story/-Wir-muessen-mutig-nach-vorne-schauen--22050469',
|
|
||||||
'md5': 'cd4cbb99b94130cff423e967cd275e5e',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '469408',
|
|
||||||
'display_id': '-Wir-muessen-mutig-nach-vorne-schauen--22050469',
|
|
||||||
'ext': 'flv',
|
|
||||||
'title': '«Wir müssen mutig nach vorne schauen»',
|
|
||||||
'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.',
|
|
||||||
'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg'
|
|
||||||
},
|
},
|
||||||
'skip': '"This video is no longer available" is shown both on the web page and in the downloaded file.',
|
|
||||||
}, {
|
}, {
|
||||||
# news article with video
|
'url': 'http://www.20min.ch/videoplayer/videoplayer.html?params=client@twentyDE|videoId@523629',
|
||||||
'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
|
|
||||||
'md5': '372917ba85ed969e176d287ae54b2f94',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '523629',
|
'id': '523629',
|
||||||
'display_id': 'So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
|
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'So kommen Sie bei Eis und Schnee sicher an',
|
'title': 'So kommen Sie bei Eis und Schnee sicher an',
|
||||||
'description': 'Schneegestöber und Glatteis führten in den letzten Tagen zu zahlreichen Strassenunfällen. Ein Experte erklärt, worauf man nun beim Autofahren achten muss.',
|
'description': 'md5:117c212f64b25e3d95747e5276863f7d',
|
||||||
'thumbnail': 'http://www.20min.ch/images/content/2/7/0/27032552/83/teaserbreit.jpg',
|
'thumbnail': r're:https?://.*\.jpg$',
|
||||||
}
|
},
|
||||||
}, {
|
'params': {
|
||||||
# YouTube embed
|
'skip_download': True,
|
||||||
'url': 'http://www.20min.ch/ro/sports/football/story/Il-marque-une-bicyclette-de-plus-de-30-metres--21115184',
|
|
||||||
'md5': 'e7e237fd98da2a3cc1422ce683df234d',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'ivM7A7SpDOs',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'GOLAZO DE CHILENA DE JAVI GÓMEZ, FINALISTA AL BALÓN DE CLM 2016',
|
|
||||||
'description': 'md5:903c92fbf2b2f66c09de514bc25e9f5a',
|
|
||||||
'upload_date': '20160424',
|
|
||||||
'uploader': 'CMM Castilla-La Mancha Media',
|
|
||||||
'uploader_id': 'RTVCM',
|
|
||||||
},
|
},
|
||||||
'add_ie': ['Youtube'],
|
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.20min.ch/videotv/?cid=44&vid=468738',
|
'url': 'http://www.20min.ch/videotv/?cid=44&vid=468738',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
|
||||||
'url': 'http://www.20min.ch/ro/sortir/cinema/story/Grandir-au-bahut--c-est-dur-18927411',
|
|
||||||
'only_matching': True,
|
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def _extract_urls(webpage):
|
||||||
|
return [m.group('url') for m in re.finditer(
|
||||||
|
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:www\.)?20min\.ch/videoplayer/videoplayer.html\?.*?\bvideoId@\d+.*?)\1',
|
||||||
|
webpage)]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
video_id = self._match_id(url)
|
||||||
video_id = mobj.group('id')
|
|
||||||
display_id = mobj.group('display_id') or video_id
|
|
||||||
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
video = self._download_json(
|
||||||
|
'http://api.20min.ch/video/%s/show' % video_id,
|
||||||
|
video_id)['content']
|
||||||
|
|
||||||
youtube_url = self._html_search_regex(
|
title = video['title']
|
||||||
r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
|
|
||||||
webpage, 'YouTube embed URL', default=None)
|
|
||||||
if youtube_url is not None:
|
|
||||||
return self.url_result(youtube_url, 'Youtube')
|
|
||||||
|
|
||||||
title = self._html_search_regex(
|
formats = [{
|
||||||
r'<h1>.*?<span>(.+?)</span></h1>',
|
'format_id': format_id,
|
||||||
webpage, 'title', default=None)
|
'url': 'http://podcast.20min-tv.ch/podcast/20min/%s%s.mp4' % (video_id, p),
|
||||||
if not title:
|
'quality': quality,
|
||||||
title = remove_end(re.sub(
|
} for quality, (format_id, p) in enumerate([('sd', ''), ('hd', 'h')])]
|
||||||
r'^20 [Mm]inuten.*? -', '', self._og_search_title(webpage)), ' - News')
|
self._sort_formats(formats)
|
||||||
|
|
||||||
if not video_id:
|
description = video.get('lead')
|
||||||
params = self._html_search_regex(
|
thumbnail = video.get('thumbnail')
|
||||||
r'<iframe[^>]+src="(?:https?:)?//www\.20min\.ch/videoplayer/videoplayer\.html\?params=(.+?[^"])"',
|
|
||||||
webpage, '20min embed URL')
|
|
||||||
video_id = self._search_regex(
|
|
||||||
r'.*videoId@(\d+)',
|
|
||||||
params, 'Video Id')
|
|
||||||
|
|
||||||
description = self._html_search_meta(
|
def extract_count(kind):
|
||||||
'description', webpage, 'description')
|
return try_get(
|
||||||
thumbnail = self._og_search_thumbnail(webpage)
|
video,
|
||||||
|
lambda x: int_or_none(x['communityobject']['thumbs_%s' % kind]))
|
||||||
|
|
||||||
formats = []
|
like_count = extract_count('up')
|
||||||
format_preferences = [('sd', ''), ('hd', 'h')]
|
dislike_count = extract_count('down')
|
||||||
for format_id, url_extension in format_preferences:
|
|
||||||
format_url = 'http://podcast.20min-tv.ch/podcast/20min/%s%s.mp4' % (video_id, url_extension)
|
|
||||||
formats.append({
|
|
||||||
'format_id': format_id,
|
|
||||||
'url': format_url,
|
|
||||||
})
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'display_id': display_id,
|
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': description,
|
'description': description,
|
||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
|
'like_count': like_count,
|
||||||
|
'dislike_count': dislike_count,
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user