X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/415fdb62500dca2e22067a05008dfbf87c75b662..7df4343e553a9942a290e5e1dffe931261ab844e:/youtube_dl/extractor/cspan.py diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index b6552c5..fbefd37 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -7,7 +7,10 @@ from ..utils import ( int_or_none, unescapeHTML, find_xpath_attr, + smuggle_url, + determine_ext, ) +from .senateisvp import SenateISVPIE class CSpanIE(InfoExtractor): @@ -27,13 +30,30 @@ class CSpanIE(InfoExtractor): 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', # For whatever reason, the served video alternates between # two different ones - #'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c', 'info_dict': { 'id': '340723', 'ext': 'mp4', 'title': 'International Health Care Models', 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967', } + }, { + 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', + 'md5': '446562a736c6bf97118e389433ed88d4', + 'info_dict': { + 'id': '342759', + 'ext': 'mp4', + 'title': 'General Motors Ignition Switch Recall', + 'duration': 14848, + 'description': 'md5:70c7c3b8fa63fa60d42772440596034c' + }, + }, { + # Video from senate.gov + 'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers', + 'info_dict': { + 'id': 'judiciary031715', + 'ext': 'flv', + 'title': 'Immigration Reforms Needed to Protect Skilled American Workers', + } }] def _real_extract(self, url): @@ -50,7 +70,7 @@ class CSpanIE(InfoExtractor): # present, otherwise this is a stripped version r'

(.*?)

' ], - webpage, 'description', flags=re.DOTALL) + webpage, 'description', flags=re.DOTALL, default=None) info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id data = self._download_json(info_url, video_id) @@ -62,7 +82,16 @@ class CSpanIE(InfoExtractor): title = find_xpath_attr(doc, './/string', 'name', 'title').text thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text + senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) + if senate_isvp_url: + surl = smuggle_url(senate_isvp_url, {'force_title': title}) + return self.url_result(surl, 'SenateISVP', video_id, title) + files = data['video']['files'] + try: + capfile = data['video']['capfile']['#text'] + except KeyError: + capfile = None entries = [{ 'id': '%s_%d' % (video_id, partnum + 1), @@ -73,11 +102,22 @@ class CSpanIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'duration': int_or_none(f.get('length', {}).get('#text')), + 'subtitles': { + 'en': [{ + 'url': capfile, + 'ext': determine_ext(capfile, 'dfxp') + }], + } if capfile else None, } for partnum, f in enumerate(files)] - return { - '_type': 'playlist', - 'entries': entries, - 'title': title, - 'id': video_id, - } + if len(entries) == 1: + entry = dict(entries[0]) + entry['id'] = video_id + return entry + else: + return { + '_type': 'playlist', + 'entries': entries, + 'title': title, + 'id': video_id, + }