github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[lifenews] Detect <iframe> (fixes #5346)

Browse source
This commit is contained in:
Yen Chi Hsuan 2015-05-04 01:24:19 +08:00
parent 1748d67aea
commit 848edeab89
1 changed files with 38 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

47
youtube_dl/extractor/lifenews.py
View file

@ -16,7 +16,7 @@ class LifeNewsIE(InfoExtractor):
IE_DESC = 'LIFE | NEWS' IE_DESC = 'LIFE | NEWS'
_VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)' _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
_TEST = { _TESTS = [{
'url': 'http://lifenews.ru/news/126342', 'url': 'http://lifenews.ru/news/126342',
'md5': 'e1b50a5c5fb98a6a544250f2e0db570a', 'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
'info_dict': { 'info_dict': {
@ -27,7 +27,19 @@ class LifeNewsIE(InfoExtractor):
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
'upload_date': '20140130', 'upload_date': '20140130',
} }
} }, {
# video in <iframe>
'url': 'http://lifenews.ru/news/152125',
'md5': '77d19a6f0886cd76bdbf44b4d971a273',
'info_dict': {
'id': '152125',
'ext': 'mp4',
'title': 'В Сети появилось видео захвата «Правым сектором» колхозных полей ',
'description': 'Жители двух поселков Днепропетровской области не простили радикалам угрозу лишения плодородных земель и пошли в лобовую. ',
'upload_date': '20150402',
'uploader': 'embed.life.ru',
}
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -36,7 +48,9 @@ def _real_extract(self, url):
webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page') webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page')
videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage) videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
if not videos: iframe_link = self._html_search_regex(
'<iframe[^>]+src="([^"]+)', webpage, 'iframe link', default=None)
if not videos and not iframe_link:
raise ExtractorError('No media links available for %s' % video_id) raise ExtractorError('No media links available for %s' % video_id)
title = self._og_search_title(webpage) title = self._og_search_title(webpage)
@ -56,17 +70,32 @@ def _real_extract(self, url):
if upload_date is not None: if upload_date is not None:
upload_date = unified_strdate(upload_date) upload_date = unified_strdate(upload_date)
common_info = {
'description': description,
'view_count': int_or_none(view_count),
'comment_count': int_or_none(comment_count),
'upload_date': upload_date,
}
def make_entry(video_id, media, video_number=None): def make_entry(video_id, media, video_number=None):
return { cur_info = dict(common_info)
cur_info.update({
'id': video_id, 'id': video_id,
'url': media[1], 'url': media[1],
'thumbnail': media[0], 'thumbnail': media[0],
'title': title if video_number is None else '%s-video%s' % (title, video_number), 'title': title if video_number is None else '%s-video%s' % (title, video_number),
'description': description, })
'view_count': int_or_none(view_count), return cur_info
'comment_count': int_or_none(comment_count),
'upload_date': upload_date, if iframe_link:
} cur_info = dict(common_info)
cur_info.update({
'_type': 'url_transparent',
'id': video_id,
'title': title,
'url': iframe_link,
})
return cur_info
if len(videos) == 1: if len(videos) == 1:
return make_entry(video_id, videos[0]) return make_entry(video_id, videos[0])