X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/ca4d08063804fb264eb0ae9cc57894198f66e1fb..d6a63f36bce16b1ad6cfc0fad712b13fdd598f1f:/youtube_dl/extractor/cspan.py diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index d573068..171820e 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -1,51 +1,183 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( - compat_urllib_parse, + int_or_none, + unescapeHTML, + find_xpath_attr, + smuggle_url, + determine_ext, + ExtractorError, + extract_attributes, ) +from .senateisvp import SenateISVPIE +from .ustream import UstreamIE + class CSpanIE(InfoExtractor): - _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)' - _TEST = { - u'url': u'http://www.c-spanvideo.org/program/HolderonV', - u'file': u'315139.flv', - u'md5': u'74a623266956f69e4df0068ab6c80fe4', - u'info_dict': { - u"title": u"Attorney General Eric Holder on Voting Rights Act Decision" + _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': '94b29a4f131ff03d23471dd6f60b6a1d', + 'info_dict': { + 'id': '315139', + 'title': 'Attorney General Eric Holder on Voting Rights Act Decision', + }, + 'playlist_mincount': 2, + 'skip': 'Regularly fails on travis, for unknown reasons', + }, { + 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', + # md5 is unstable + 'info_dict': { + 'id': 'c4486943', + 'ext': 'mp4', + 'title': 'CSPAN - International Health Care Models', + 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967', + } + }, { + 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', + 'info_dict': { + 'id': '342759', + 'title': 'General Motors Ignition Switch Recall', + }, + 'playlist_mincount': 6, + }, { + # 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': 'mp4', + 'title': 'Immigration Reforms Needed to Protect Skilled American Workers', + }, + 'params': { + 'skip_download': True, # m3u8 downloads + } + }, { + # Ustream embedded video + 'url': 'https://www.c-span.org/video/?114917-1/armed-services', + 'info_dict': { + 'id': '58428542', + 'ext': 'flv', + 'title': 'USHR07 Armed Services Committee', + 'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee', + 'timestamp': 1423060374, + 'upload_date': '20150204', + 'uploader': 'HouseCommittee', + 'uploader_id': '12987475', }, - u'skip': u'Requires rtmpdump' - } + }] + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - prog_name = mobj.group(1) - webpage = self._download_webpage(url, prog_name) - video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id') - data = compat_urllib_parse.urlencode({'programid': video_id, - 'dynamic':'1'}) - info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data - video_info = self._download_webpage(info_url, video_id, u'Downloading video info') - - self.report_extraction(video_id) - - title = self._html_search_regex(r'(.*?)', - video_info, 'title') - description = self._html_search_regex(r'(.*?)', - video_info, 'video url') - url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443') - path = self._search_regex(r'(.*?)', - video_info, 'rtmp play path') - - return {'id': video_id, - 'title': title, - 'ext': 'flv', - 'url': url, - 'play_path': path, + video_id = self._match_id(url) + video_type = None + webpage = self._download_webpage(url, video_id) + + ustream_url = UstreamIE._extract_url(webpage) + if ustream_url: + return self.url_result(ustream_url, UstreamIE.ie_key()) + + if '&vod' not in url: + bc = self._search_regex( + r"(<[^>]+id='brightcove-player-embed'[^>]+>)", + webpage, 'brightcove embed', default=None) + if bc: + bc_attr = extract_attributes(bc) + bc_url = self.BRIGHTCOVE_URL_TEMPLATE % ( + bc_attr.get('data-bcaccountid', '3162030207001'), + bc_attr.get('data-noprebcplayerid', 'SyGGpuJy3g'), + bc_attr.get('data-newbcplayerid', 'default'), + bc_attr['data-bcid']) + return self.url_result(smuggle_url(bc_url, {'source_url': url})) + + # 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() + video_type = 'clip' if video_type == 'id' else 'program' + else: + 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://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), + video_id) + + description = self._html_search_meta('description', webpage) + + title = find_xpath_attr(doc, './/string', 'name', 'title').text + thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text + + files = data['files'] + capfile = get_text_attr(data, 'capfile') + + 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': self._og_search_thumbnail(webpage), - } + '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]) + entry['id'] = 'c' + video_id if video_type == 'clip' else video_id + return entry + else: + return { + '_type': 'playlist', + 'entries': entries, + 'title': title, + 'id': 'c' + video_id if video_type == 'clip' else video_id, + }