Cool_Tools/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-25 00:00:48 +01:00
Code Issues Packages Projects Releases Wiki Activity

[xvideos] Extract html5 player formats (Closes #9495)

Browse Source
This commit is contained in:
Sergey M․ 2016-05-15 03:38:04 +06:00
parent ed56f26039
commit 69c9cc2716
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 21 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
youtube_dl/extractor/xvideos.py
View File

@ -8,7 +8,6 @@
clean_html, clean_html,
ExtractorError, ExtractorError,
determine_ext, determine_ext,
sanitized_Request,
) )
@ -25,8 +24,6 @@ class XVideosIE(InfoExtractor):
} }
} }
_ANDROID_USER_AGENT = 'Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19'
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
@ -35,31 +32,34 @@ def _real_extract(self, url):
if mobj: if mobj:
raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True) raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
video_url = compat_urllib_parse_unquote(
self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
video_title = self._html_search_regex( video_title = self._html_search_regex(
r'<title>(.*?)\s+-\s+XVID', webpage, 'title') r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
video_thumbnail = self._search_regex( video_thumbnail = self._search_regex(
r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False) r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
formats = [{ formats = []
'url': video_url,
}]
android_req = sanitized_Request(url) video_url = compat_urllib_parse_unquote(self._search_regex(
android_req.add_header('User-Agent', self._ANDROID_USER_AGENT) r'flv_url=(.+?)&', webpage, 'video URL', default=''))
android_webpage = self._download_webpage(android_req, video_id, fatal=False) if video_url:
formats.append({'url': video_url})
if android_webpage is not None: player_args = self._search_regex(
player_params_str = self._search_regex( r'(?s)new\s+HTML5Player\((.+?)\)', webpage, ' html5 player', default=None)
'mobileReplacePlayerDivTwoQual\(([^)]+)\)', if player_args:
android_webpage, 'player parameters', default='') for arg in player_args.split(','):
player_params = list(map(lambda s: s.strip(' \''), player_params_str.split(','))) format_url = self._search_regex(
if player_params: r'(["\'])(?P<url>https?://.+?)\1', arg, 'url',
formats.extend([{ default=None, group='url')
'url': param, if not format_url:
'preference': -10, continue
} for param in player_params if determine_ext(param) == 'mp4']) ext = determine_ext(format_url)
if ext == 'mp4':
formats.append({'url': format_url})
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
self._sort_formats(formats) self._sort_formats(formats)
@ -67,7 +67,6 @@ def _real_extract(self, url):
'id': video_id, 'id': video_id,
'formats': formats, 'formats': formats,
'title': video_title, 'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail, 'thumbnail': video_thumbnail,
'age_limit': 18, 'age_limit': 18,
} }