X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9815bb0a551468e4939cacfffbc2d5cb8dd12431..63a6927374492ef47c8fd6de67d0760ace4dd0ed:/youtube_dl/extractor/bliptv.py diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index df2ad4b..5e33a69 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -24,6 +24,17 @@ class BlipTVIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$' _URL_EXT = r'^.*\.([a-z0-9]+)$' IE_NAME = u'blip.tv' + _TEST = { + u'url': u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352', + u'file': u'5779306.m4v', + u'md5': u'80baf1ec5c3d2019037c1c707d676b9f', + u'info_dict': { + u"upload_date": u"20111205", + u"description": u"md5:9bc31f227219cde65e47eeec8d2dc596", + u"uploader": u"Comic Book Resources - CBR TV", + u"title": u"CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3" + } + } def report_direct_download(self, title): """Report information extraction.""" @@ -40,8 +51,7 @@ class BlipTVIE(InfoExtractor): url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id') urlp = compat_urllib_parse_urlparse(url) if urlp.path.startswith('/play/'): - request = compat_urllib_request.Request(url) - response = compat_urllib_request.urlopen(request) + response = self._request_webpage(url, None, False) redirecturl = response.geturl() rurlp = compat_urllib_parse_urlparse(redirecturl) file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2] @@ -58,25 +68,23 @@ class BlipTVIE(InfoExtractor): request.add_header('User-Agent', 'iTunes/10.6.1') self.report_extraction(mobj.group(1)) info = None - try: - urlh = compat_urllib_request.urlopen(request) - if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download - basename = url.split('/')[-1] - title,ext = os.path.splitext(basename) - title = title.decode('UTF-8') - ext = ext.replace('.', '') - self.report_direct_download(title) - info = { - 'id': title, - 'url': url, - 'uploader': None, - 'upload_date': None, - 'title': title, - 'ext': ext, - 'urlhandle': urlh - } - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) + urlh = self._request_webpage(request, None, False, + u'unable to download video info webpage') + if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download + basename = url.split('/')[-1] + title,ext = os.path.splitext(basename) + title = title.decode('UTF-8') + ext = ext.replace('.', '') + self.report_direct_download(title) + info = { + 'id': title, + 'url': url, + 'uploader': None, + 'upload_date': None, + 'title': title, + 'ext': ext, + 'urlhandle': urlh + } if info is None: # Regular URL try: json_code_bytes = urlh.read() @@ -92,14 +100,19 @@ class BlipTVIE(InfoExtractor): data = json_data upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') - video_url = data['media']['url'] + if 'additionalMedia' in data: + formats = sorted(data['additionalMedia'], key=lambda f: int(f['media_height'])) + best_format = formats[-1] + video_url = best_format['url'] + else: + video_url = data['media']['url'] umobj = re.match(self._URL_EXT, video_url) if umobj is None: raise ValueError('Can not determine filename extension') ext = umobj.group(1) info = { - 'id': data['item_id'], + 'id': compat_str(data['item_id']), 'url': video_url, 'uploader': data['display_name'], 'upload_date': upload_date, @@ -173,5 +186,5 @@ class BlipTVUserIE(InfoExtractor): pagenum += 1 urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids] - url_entries = [self.url_result(url, 'BlipTV') for url in urls] + url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls] return [self.playlist_result(url_entries, playlist_title = username)]