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

use search_regex in new IEs

Browse source
This commit is contained in:
Filippo Valsorda 2013-06-07 11:46:03 +02:00
parent be95cac157
commit 8409501206
1 changed files with 22 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

44
youtube_dl/InfoExtractors.py
View file

@ -3347,7 +3347,7 @@ class FunnyOrDieIE(InfoExtractor):
title = clean_html(title) title = clean_html(title)
video_description = self._search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"', video_description = self._search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
webpage, u'description', flags=re.DOTALL) webpage, u'description', fatal=False, flags=re.DOTALL)
if video_description: video_description = unescapeHTML(video_description) if video_description: video_description = unescapeHTML(video_description)
info = { info = {
@ -4312,6 +4312,7 @@ class XHamsterIE(InfoExtractor):
video_id = mobj.group('id') video_id = mobj.group('id')
mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
webpage = self._download_webpage(mrss_url, video_id) webpage = self._download_webpage(mrss_url, video_id)
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage) mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None: if mobj is None:
raise ExtractorError(u'Unable to extract media URL') raise ExtractorError(u'Unable to extract media URL')
@ -4321,32 +4322,26 @@ class XHamsterIE(InfoExtractor):
video_url = mobj.group('server')+'/key='+mobj.group('file') video_url = mobj.group('server')+'/key='+mobj.group('file')
video_extension = video_url.split('.')[-1] video_extension = video_url.split('.')[-1]
mobj = re.search(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage) video_title = self._search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
if mobj is None: webpage, u'title')
raise ExtractorError(u'Unable to extract title') video_title = unescapeHTML(video_title)
video_title = unescapeHTML(mobj.group('title'))
mobj = re.search(r'<span>Description: </span>(?P<description>[^<]+)', webpage) video_description = self._search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
if mobj is None: webpage, u'description', fatal=False)
video_description = u'' if video_description: video_description = unescapeHTML(video_description)
else:
video_description = unescapeHTML(mobj.group('description'))
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
if mobj is None: if mobj:
raise ExtractorError(u'Unable to extract upload date')
video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
mobj = re.search(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^>]+)', webpage)
if mobj is None:
video_uploader_id = u'anonymous'
else: else:
video_uploader_id = mobj.group('uploader_id') video_upload_date = None
self._downloader.report_warning(u'Unable to extract upload date')
mobj = re.search(r'\'image\':\'(?P<thumbnail>[^\']+)\'', webpage) video_uploader_id = self._search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^>]+)',
if mobj is None: webpage, u'uploader id', default=u'anonymous')
raise ExtractorError(u'Unable to extract thumbnail URL')
video_thumbnail = mobj.group('thumbnail') video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
webpage, u'thumbnail', fatal=False)
return [{ return [{
'id': video_id, 'id': video_id,
@ -4377,10 +4372,9 @@ class HypemIE(InfoExtractor):
cookie = urlh.headers.get('Set-Cookie', '') cookie = urlh.headers.get('Set-Cookie', '')
self.report_extraction(track_id) self.report_extraction(track_id)
mobj = re.search(r'<script type="application/json" id="displayList-data">(.*?)</script>', response, flags=re.MULTILINE|re.DOTALL)
if mobj is None: html_tracks = self._search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
raise ExtractorError(u'Unable to extrack tracks') response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
html_tracks = mobj.group(1).strip()
try: try:
track_list = json.loads(html_tracks) track_list = json.loads(html_tracks)
track = track_list[u'tracks'][0] track = track_list[u'tracks'][0]