X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcspan.py;h=84b36f44cfac7bd45a8a7d28adb6767093a7d19b;hb=b5aad37f6bdc72acaca198202dc9f7eaa3185e51;hp=994e080d5d24b7d719ffff39037bd4c77acb0e4a;hpb=30787f7259c4e6a08f691cc691f14fa0c8fe4b87;p=youtube-dl diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 994e080d5..84b36f44c 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -9,16 +9,17 @@ from ..utils import ( find_xpath_attr, smuggle_url, determine_ext, + ExtractorError, ) from .senateisvp import SenateISVPIE class CSpanIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P[0-9a-f]+)' + _VALID_URL = r'https?://(?:www\.)?c-span\.org/video/\?(?P[0-9a-f]+)' IE_DESC = 'C-SPAN' _TESTS = [{ 'url': 'http://www.c-span.org/video/?313572-1/HolderonV', - 'md5': '067803f994e049b455a58b16e5aab442', + 'md5': '94b29a4f131ff03d23471dd6f60b6a1d', 'info_dict': { 'id': '315139', 'ext': 'mp4', @@ -28,7 +29,7 @@ class CSpanIE(InfoExtractor): 'skip': 'Regularly fails on travis, for unknown reasons', }, { 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', - 'md5': '4eafd1e91a75d2b1e6a3cbd0995816a2', + 'md5': '8e5fbfabe6ad0f89f3012a7943c1287b', 'info_dict': { 'id': 'c4486943', 'ext': 'mp4', @@ -37,7 +38,7 @@ class CSpanIE(InfoExtractor): } }, { 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', - 'md5': '446562a736c6bf97118e389433ed88d4', + 'md5': '2ae5051559169baadba13fc35345ae74', 'info_dict': { 'id': '342759', 'ext': 'mp4', @@ -57,22 +58,37 @@ class CSpanIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + video_type = None webpage = self._download_webpage(url, video_id) - matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage) - if matches: + # We first look for clipid, because clipprog always appears before + patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')] + results = list(filter(None, (re.search(p, webpage) for p in patterns))) + if results: + matches = results[0] video_type, video_id = matches.groups() - if video_type == 'prog': - video_type = 'program' + video_type = 'clip' if video_type == 'id' else 'program' else: - senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) - if senate_isvp_url: - title = self._og_search_title(webpage) - surl = smuggle_url(senate_isvp_url, {'force_title': title}) - return self.url_result(surl, 'SenateISVP', video_id, title) + m = re.search(r'data-(?Pclip|prog)id=["\'](?P\d+)', webpage) + if m: + video_id = m.group('id') + video_type = 'program' if m.group('type') == 'prog' else 'clip' + else: + senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) + if senate_isvp_url: + title = self._og_search_title(webpage) + surl = smuggle_url(senate_isvp_url, {'force_title': title}) + return self.url_result(surl, 'SenateISVP', video_id, title) + if video_type is None or video_id is None: + raise ExtractorError('unable to find video id and type') + + def get_text_attr(d, attr): + return d.get(attr, {}).get('#text') data = self._download_json( - 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id), - video_id) + 'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id), + video_id)['video'] + if data['@status'] != 'Success': + raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True) doc = self._download_xml( 'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id), @@ -83,28 +99,43 @@ class CSpanIE(InfoExtractor): title = find_xpath_attr(doc, './/string', 'name', 'title').text thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text - files = data['video']['files'] - try: - capfile = data['video']['capfile']['#text'] - except KeyError: - capfile = None + files = data['files'] + capfile = get_text_attr(data, 'capfile') - entries = [{ - 'id': '%s_%d' % (video_id, partnum + 1), - 'title': ( - title if len(files) == 1 else - '%s part %d' % (title, partnum + 1)), - 'url': unescapeHTML(f['path']['#text']), - '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)] + entries = [] + for partnum, f in enumerate(files): + formats = [] + for quality in f['qualities']: + formats.append({ + 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')), + 'url': unescapeHTML(get_text_attr(quality, 'file')), + 'height': int_or_none(get_text_attr(quality, 'height')), + 'tbr': int_or_none(get_text_attr(quality, 'bitrate')), + }) + if not formats: + path = unescapeHTML(get_text_attr(f, 'path')) + if not path: + continue + formats = self._extract_m3u8_formats( + path, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }] + self._sort_formats(formats) + entries.append({ + 'id': '%s_%d' % (video_id, partnum + 1), + 'title': ( + title if len(files) == 1 else + '%s part %d' % (title, partnum + 1)), + 'formats': formats, + 'description': description, + 'thumbnail': thumbnail, + 'duration': int_or_none(get_text_attr(f, 'length')), + 'subtitles': { + 'en': [{ + 'url': capfile, + 'ext': determine_ext(capfile, 'dfxp') + }], + } if capfile else None, + }) if len(entries) == 1: entry = dict(entries[0])