X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcspan.py;h=7b685d157ddc07de54d59ba52cfc7db0940f6eb2;hb=3047121c639428235191ff5f7afbda7ecda38779;hp=e54009622aa353d618326ca51044aa567c2eef55;hpb=11577ec0542163cbae5ad97869ea56bbd46bbc37;p=youtube-dl diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index e54009622..7b685d157 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -1,49 +1,133 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor from ..utils import ( + int_or_none, unescapeHTML, + find_xpath_attr, + smuggle_url, + determine_ext, + ExtractorError, ) +from .senateisvp import SenateISVPIE class CSpanIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?c-spanvideo\.org/program/(?P.*)' + _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P[0-9a-f]+)' IE_DESC = 'C-SPAN' - _TEST = { - 'url': 'http://www.c-spanvideo.org/program/HolderonV', - 'file': '315139.mp4', - 'md5': '8e44ce11f0f725527daccc453f553eb0', + _TESTS = [{ + 'url': 'http://www.c-span.org/video/?313572-1/HolderonV', + 'md5': '94b29a4f131ff03d23471dd6f60b6a1d', 'info_dict': { + 'id': '315139', + 'ext': 'mp4', 'title': 'Attorney General Eric Holder on Voting Rights Act Decision', - 'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in [Shelby County v. Holder] in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.', + 'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.', }, 'skip': 'Regularly fails on travis, for unknown reasons', - } + }, { + 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', + 'md5': '8e5fbfabe6ad0f89f3012a7943c1287b', + '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', + 'md5': '2ae5051559169baadba13fc35345ae74', + 'info_dict': { + 'id': '342759', + 'ext': 'mp4', + 'title': 'General Motors Ignition Switch Recall', + 'duration': 14848, + 'description': 'md5:118081aedd24bf1d3b68b3803344e7f3' + }, + }, { + # 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): - mobj = re.match(self._VALID_URL, url) - prog_name = mobj.group('name') - webpage = self._download_webpage(url, prog_name) - video_id = self._search_regex(r'prog(?:ram)?id=(.*?)&', webpage, 'video id') - - title = self._html_search_regex( - r'\n\s*]*>(.*?)', webpage, 'title') - description = self._og_search_description(webpage) - - info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id - data_json = self._download_webpage( - info_url, video_id, 'Downloading video info') - data = json.loads(data_json) - - url = unescapeHTML(data['video']['files'][0]['path']['#text']) - - return { - 'id': video_id, - 'title': title, - 'url': url, - 'description': description, - 'thumbnail': self._og_search_thumbnail(webpage), - } + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage) + if matches: + video_type, video_id = matches.groups() + if video_type == 'prog': + video_type = '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) + + 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')), + }) + 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]) + 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, + }