etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-29 03:23:02 +00:00
Code Issues Projects Releases Wiki Activity

_download_webpage helper function

Browse source
This commit is contained in:
Philipp Hagemeister 2013-01-01 20:43:43 +01:00
parent 1c256f7047
commit d830b7c297
1 changed files with 15 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
youtube_dl/InfoExtractors.py
View file

@ -105,6 +105,20 @@ def _real_extract(self, url):
def IE_NAME(self): def IE_NAME(self):
return type(self).__name__[:-2] return type(self).__name__[:-2]
def _download_webpage(self, url, video_id, note=None, errnote=None):
if note is None:
note = u'Downloading video webpage'
self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note))
try:
urlh = compat_urllib_request.urlopen(url)
webpage_bytes = urlh.read()
return webpage_bytes.decode('utf-8', 'replace')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
if errnote is None:
errnote = u'Unable to download webpage'
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)))
class YoutubeIE(InfoExtractor): class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com.""" """Information extractor for youtube.com."""
@ -3803,12 +3817,7 @@ def _real_extract(self, url):
m = re.match(self._VALID_URL, url) m = re.match(self._VALID_URL, url)
video_id = m.group('videoID') video_id = m.group('videoID')
video_url = u'http://tcdn.ustream.tv/video/%s' % video_id video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
try: webpage = self._download_webpage(url, video_id)
urlh = compat_urllib_request.urlopen(url)
webpage_bytes = urlh.read()
webpage = webpage_bytes.decode('utf-8', 'ignore')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'unable to download webpage: %s' % compat_str(err))
m = re.search(r'data-title="(?P<title>.+)"',webpage) m = re.search(r'data-title="(?P<title>.+)"',webpage)
title = m.group('title') title = m.group('title')
m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage) m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)