|
|
@ -731,99 +731,6 @@ class DailymotionIE(InfoExtractor): |
|
|
|
}] |
|
|
|
|
|
|
|
|
|
|
|
class GoogleIE(InfoExtractor): |
|
|
|
"""Information extractor for video.google.com.""" |
|
|
|
|
|
|
|
_VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' |
|
|
|
IE_NAME = u'video.google' |
|
|
|
|
|
|
|
def __init__(self, downloader=None): |
|
|
|
InfoExtractor.__init__(self, downloader) |
|
|
|
|
|
|
|
def report_download_webpage(self, video_id): |
|
|
|
"""Report webpage download.""" |
|
|
|
self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) |
|
|
|
|
|
|
|
def report_extraction(self, video_id): |
|
|
|
"""Report information extraction.""" |
|
|
|
self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) |
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
|
# Extract id from URL |
|
|
|
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(1) |
|
|
|
|
|
|
|
video_extension = 'mp4' |
|
|
|
|
|
|
|
# Retrieve video webpage to extract further information |
|
|
|
request = compat_urllib_request.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) |
|
|
|
try: |
|
|
|
self.report_download_webpage(video_id) |
|
|
|
webpage = compat_urllib_request.urlopen(request).read() |
|
|
|
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
|
|
|
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) |
|
|
|
return |
|
|
|
|
|
|
|
# Extract URL, uploader, and title from webpage |
|
|
|
self.report_extraction(video_id) |
|
|
|
mobj = re.search(r"download_url:'([^']+)'", webpage) |
|
|
|
if mobj is None: |
|
|
|
video_extension = 'flv' |
|
|
|
mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) |
|
|
|
if mobj is None: |
|
|
|
self._downloader.trouble(u'ERROR: unable to extract media URL') |
|
|
|
return |
|
|
|
mediaURL = compat_urllib_parse.unquote(mobj.group(1)) |
|
|
|
mediaURL = mediaURL.replace('\\x3d', '\x3d') |
|
|
|
mediaURL = mediaURL.replace('\\x26', '\x26') |
|
|
|
|
|
|
|
video_url = mediaURL |
|
|
|
|
|
|
|
mobj = re.search(r'<title>(.*)</title>', webpage) |
|
|
|
if mobj is None: |
|
|
|
self._downloader.trouble(u'ERROR: unable to extract title') |
|
|
|
return |
|
|
|
video_title = mobj.group(1).decode('utf-8') |
|
|
|
|
|
|
|
# Extract video description |
|
|
|
mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage) |
|
|
|
if mobj is None: |
|
|
|
self._downloader.trouble(u'ERROR: unable to extract video description') |
|
|
|
return |
|
|
|
video_description = mobj.group(1).decode('utf-8') |
|
|
|
if not video_description: |
|
|
|
video_description = 'No description available.' |
|
|
|
|
|
|
|
# Extract video thumbnail |
|
|
|
if self._downloader.params.get('forcethumbnail', False): |
|
|
|
request = compat_urllib_request.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) |
|
|
|
try: |
|
|
|
webpage = compat_urllib_request.urlopen(request).read() |
|
|
|
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
|
|
|
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) |
|
|
|
return |
|
|
|
mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) |
|
|
|
if mobj is None: |
|
|
|
self._downloader.trouble(u'ERROR: unable to extract video thumbnail') |
|
|
|
return |
|
|
|
video_thumbnail = mobj.group(1) |
|
|
|
else: # we need something to pass to process_info |
|
|
|
video_thumbnail = '' |
|
|
|
|
|
|
|
return [{ |
|
|
|
'id': video_id.decode('utf-8'), |
|
|
|
'url': video_url.decode('utf-8'), |
|
|
|
'uploader': None, |
|
|
|
'upload_date': None, |
|
|
|
'title': video_title, |
|
|
|
'ext': video_extension.decode('utf-8'), |
|
|
|
}] |
|
|
|
|
|
|
|
|
|
|
|
class PhotobucketIE(InfoExtractor): |
|
|
|
"""Information extractor for photobucket.com.""" |
|
|
|
|
|
|
|