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

Fix comedycentral: newest

Browse source
This commit is contained in:
Philipp Hagemeister 2013-05-04 02:53:26 +02:00
parent 95464f14d1
commit 480b6c1e8b
1 changed files with 12 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
youtube_dl/InfoExtractors.py
View file

@ -124,8 +124,8 @@ class InfoExtractor(object):
errnote = u'Unable to download webpage' errnote = u'Unable to download webpage'
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the data of the page as a string """ """ Returns a tuple (page content as string, URL handle) """
urlh = self._request_webpage(url_or_request, video_id, note, errnote) urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '') content_type = urlh.headers.get('Content-Type', '')
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
@ -142,7 +142,12 @@ class InfoExtractor(object):
self.to_screen(u'Dumping request to ' + url) self.to_screen(u'Dumping request to ' + url)
dump = base64.b64encode(webpage_bytes).decode('ascii') dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump) self._downloader.to_screen(dump)
return webpage_bytes.decode(encoding, 'replace') content = webpage_bytes.decode(encoding, 'replace')
return (content, urlh)
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the data of the page as a string """
return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
def to_screen(self, msg): def to_screen(self, msg):
"""Print msg to screen, prefixing it with '[ie_name]'""" """Print msg to screen, prefixing it with '[ie_name]'"""
@ -2265,16 +2270,14 @@ class ComedyCentralIE(InfoExtractor):
epTitle = mobj.group('episode') epTitle = mobj.group('episode')
self.report_extraction(epTitle) self.report_extraction(epTitle)
webpage = self._download_webpage(url, epTitle) webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
if dlNewest: if dlNewest:
url = htmlHandle.geturl() url = htmlHandle.geturl()
mobj = re.match(self._VALID_URL, url, re.VERBOSE) mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None: if mobj is None:
self._downloader.report_error(u'Invalid redirected URL: ' + url) raise ExtractorError(u'Invalid redirected URL: ' + url)
return
if mobj.group('episode') == '': if mobj.group('episode') == '':
self._downloader.report_error(u'Redirected URL is still not specific: ' + url) raise ExtractorError(u'Redirected URL is still not specific: ' + url)
return
epTitle = mobj.group('episode') epTitle = mobj.group('episode')
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
@ -2286,8 +2289,7 @@ class ComedyCentralIE(InfoExtractor):
altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
if len(altMovieParams) == 0: if len(altMovieParams) == 0:
self._downloader.report_error(u'unable to find Flash URL in webpage ' + url) raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
return
else: else:
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]