CollegeHumor IE

This commit is contained in:
Philipp Hagemeister 2011-10-12 21:13:43 +02:00
parent 7a2cf5455c
commit 8d89fbae5a
1 changed files with 78 additions and 1 deletions

View File

@ -1236,7 +1236,7 @@ class YoutubeIE(InfoExtractor):
# Get video webpage
self.report_video_webpage_download(video_id)
request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
try:
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -3306,6 +3306,82 @@ class EscapistIE(InfoExtractor):
self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
class CollegeHumorIE(InfoExtractor):
"""Information extractor for collegehumor.com"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
IE_NAME = u'collegehumor'
def report_webpage(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
def _simplify_title(self, title):
res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
res = res.strip(ur'_')
return res
def _real_extract(self, url):
htmlParser = HTMLParser.HTMLParser()
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
video_id = mobj.group('videoid')
self.report_webpage(video_id)
request = urllib2.Request(url)
try:
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
return
m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
if m is None:
self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
return
internal_video_id = m.group('internalvideoid')
info = {
'id': video_id,
'internal_id': internal_video_id,
}
self.report_extraction(video_id)
xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
try:
metaXml = urllib2.urlopen(xmlUrl).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
return
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
videoNode = mdoc.findall('./video')[0]
info['description'] = videoNode.findall('./description')[0].text
info['title'] = videoNode.findall('./caption')[0].text
info['stitle'] = self._simplify_title(info['title'])
info['url'] = videoNode.findall('./file')[0].text
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
info['ext'] = info['url'].rpartition('.')[2]
info['format'] = info['ext']
except IndexError:
self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
return
self._downloader.increment_downloads()
try:
self._downloader.process_info(info)
except UnavailableVideoError, err:
self._downloader.trouble(u'\nERROR: unable to download video')
class PostProcessor(object):
"""Post Processor class.
@ -3701,6 +3777,7 @@ def gen_extractors():
MyVideoIE(),
ComedyCentralIE(),
EscapistIE(),
CollegeHumorIE(),
GenericIE()
]