X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bddc9fc577d16b1428924bf8a5c37ef1d9295f14..779bc665c512f2802f1436a30b6b09ee7ad83e02:/youtube_dl/extractor/metacafe.py diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 66d6554..6436c05 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -1,73 +1,143 @@ +from __future__ import unicode_literals + import re -import socket from .common import InfoExtractor from ..utils import ( - compat_http_client, compat_parse_qs, - compat_urllib_error, compat_urllib_parse, compat_urllib_request, - compat_str, - + determine_ext, ExtractorError, ) -class MetacafeIE(InfoExtractor): - """Information Extractor for metacafe.com.""" - _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' +class MetacafeIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' _DISCLAIMER = 'http://www.metacafe.com/family_filter/' _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' - IE_NAME = u'metacafe' + IE_NAME = 'metacafe' + _TESTS = [ + # Youtube video + { + 'add_ie': ['Youtube'], + 'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/', + 'info_dict': { + 'id': '_aUehQsCQtM', + 'ext': 'mp4', + 'upload_date': '20090102', + 'title': 'The Electric Company | "Short I" | PBS KIDS GO!', + 'description': 'md5:2439a8ef6d5a70e380c22f5ad323e5a8', + 'uploader': 'PBS', + 'uploader_id': 'PBS' + } + }, + # Normal metacafe video + { + 'url': 'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/', + 'md5': '6e0bca200eaad2552e6915ed6fd4d9ad', + 'info_dict': { + 'id': '11121940', + 'ext': 'mp4', + 'title': 'News: Stuff You Won\'t Do with Your PlayStation 4', + 'uploader': 'ign', + 'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.', + }, + }, + # AnyClip video + { + 'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/', + 'info_dict': { + 'id': 'an-dVVXnuY7Jh77J', + 'ext': 'mp4', + 'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3', + 'uploader': 'anyclip', + 'description': 'md5:38c711dd98f5bb87acf973d573442e67', + }, + }, + # age-restricted video + { + 'url': 'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/', + 'md5': '98dde7c1a35d02178e8ab7560fe8bd09', + 'info_dict': { + 'id': '5186653', + 'ext': 'mp4', + 'title': 'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.', + 'uploader': 'Dwayne Pipe', + 'description': 'md5:950bf4c581e2c059911fa3ffbe377e4b', + 'age_limit': 18, + }, + }, + # cbs video + { + 'url': 'http://www.metacafe.com/watch/cb-8VD4r_Zws8VP/open_this_is_face_the_nation_february_9/', + 'info_dict': { + 'id': '8VD4r_Zws8VP', + 'ext': 'flv', + 'title': 'Open: This is Face the Nation, February 9', + 'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476', + 'duration': 96, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + ] def report_disclaimer(self): - """Report disclaimer retrieval.""" - self.to_screen(u'Retrieving disclaimer') + self.to_screen('Retrieving disclaimer') def _real_initialize(self): # Retrieve disclaimer - request = compat_urllib_request.Request(self._DISCLAIMER) - try: - self.report_disclaimer() - compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err)) + self.report_disclaimer() + self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer') # Confirm age disclaimer_form = { 'filters': '0', 'submit': "Continue - I'm over 18", - } + } request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) - try: - self.report_age_confirmation() - compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + self.report_age_confirmation() + self._download_webpage(request, None, False, 'Unable to confirm age') def _real_extract(self, url): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) video_id = mobj.group(1) - # Check if video comes from YouTube - mobj2 = re.match(r'^yt-(.*)$', video_id) - if mobj2 is not None: - return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] + # the video may come from an external site + m_external = re.match('^(\w{2})-(.*)$', video_id) + if m_external is not None: + prefix, ext_id = m_external.groups() + # Check if video comes from YouTube + if prefix == 'yt': + return self.url_result('http://www.youtube.com/watch?v=%s' % ext_id, 'Youtube') + # CBS videos use theplatform.com + if prefix == 'cb': + return self.url_result('theplatform:%s' % ext_id, 'ThePlatform') # Retrieve video webpage to extract further information - webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id) + req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) + + # AnyClip videos require the flashversion cookie so that we get the link + # to the mp4 file + mobj_an = re.match(r'^an-(.*?)$', video_id) + if mobj_an: + req.headers['Cookie'] = 'flashVersion=0;' + webpage = self._download_webpage(req, video_id) # Extract URL, uploader and title from webpage self.report_extraction(video_id) mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) if mobj is not None: mediaURL = compat_urllib_parse.unquote(mobj.group(1)) - video_extension = mediaURL[-3:] + video_ext = mediaURL[-3:] # Extract gdaKey if available mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) @@ -77,34 +147,44 @@ class MetacafeIE(InfoExtractor): gdaKey = mobj.group(1) video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) else: - mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract media URL') - vardict = compat_parse_qs(mobj.group(1)) - if 'mediaData' not in vardict: - raise ExtractorError(u'Unable to extract media URL') - mobj = re.search(r'"mediaURL":"(?Phttp.*?)",(.*?)"key":"(?P.*?)"', vardict['mediaData'][0]) - if mobj is None: - raise ExtractorError(u'Unable to extract media URL') - mediaURL = mobj.group('mediaURL').replace('\\/', '/') - video_extension = mediaURL[-3:] - video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) - - mobj = re.search(r'(?im)(.*) - Video', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract title') - video_title = mobj.group(1).decode('utf-8') - - mobj = re.search(r'submitter=(.*?);', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract uploader nickname') - video_uploader = mobj.group(1) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] + mobj = re.search(r'