From 52524e85f40867d3cd1b63970e7bb05baad8748f Mon Sep 17 00:00:00 2001 From: Shiyang Zhu Date: Sat, 10 Dec 2022 15:16:03 -0500 Subject: [PATCH] _real_extract() now iterates through possible manifest URLS to find the m3u8. --- youtube_dl/extractor/senateisvp.py | 165 ++++++++++++++++------------- 1 file changed, 92 insertions(+), 73 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index f294726f4..f56f4567f 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -5,50 +5,52 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, + url_or_none, + parse_duration, unsmuggle_url, ) from ..compat import ( compat_parse_qs, - compat_urlparse, ) - class SenateISVPIE(InfoExtractor): + # committee --> [stream_number, stream_domain, stream_id, msl3] _COMM_MAP = { - 'ag': [76440, 'https://ag-f.akamaihd.net', 2036803, 'agriculture'], - 'aging': [76442, 'https://aging-f.akamaihd.net', 2036801, 'aging'], - 'approps': [76441, 'https://approps-f.akamaihd.net', 2036802, 'appropriations'], - 'armed': [76445, 'https://armed-f.akamaihd.net', 2036800, 'armedservices'], - 'banking': [76446, 'https://banking-f.akamaihd.net', 2036799, 'banking'], - 'budget': [76447, 'https://budget-f.akamaihd.net', 2036798, 'budget'], - 'cecc': [76486, 'https://srs-f.akamaihd.net', 2036782, 'srs_cecc'], - 'commerce': [80177, 'https://commerce1-f.akamaihd.net', 2036779, 'commerce'], - 'csce': [75229, 'https://srs-f.akamaihd.net', 2036777, 'srs_srs'], - 'dpc': [76590, 'https://dpc-f.akamaihd.net', None, 'dpc'], - 'energy': [76448, 'https://energy-f.akamaihd.net', 2036797, 'energy'], - 'epw': [76478, 'https://epw-f.akamaihd.net', 2036783, 'environment'], - 'ethics': [76449, 'https://ethics-f.akamaihd.net', 2036796, 'ethics'], - 'finance': [76450, 'https://finance-f.akamaihd.net', 2036795, 'finance_finance'], - 'foreign': [76451, 'https://foreign-f.akamaihd.net', 2036794, 'foreignrelations'], - 'govtaff': [76453, 'https://govtaff-f.akamaihd.net', 2036792, 'hsgac'], - 'help': [76452, 'https://help-f.akamaihd.net', 2036793, 'help'], - 'indian': [76455, 'https://indian-f.akamaihd.net', 2036791, 'indianaffairs'], - 'intel': [76456, 'https://intel-f.akamaihd.net', 2036790, 'intelligence'], - 'intlnarc': [76457, 'https://intlnarc-f.akamaihd.net', None, 'internationalnarcoticscaucus'], - 'jccic': [85180, 'https://jccic-f.akamaihd.net', 2036778, 'jccic'], - 'jec': [76458, 'https://jec-f.akamaihd.net', 2036789, 'jointeconomic'], - 'judiciary': [76459, 'https://judiciary-f.akamaihd.net', 2036788,'judiciary'], - 'rpc': [76591, 'https://rpc-f.akamaihd.net', None, 'rpc'], - 'rules': [76460, 'https://rules-f.akamaihd.net', 2036787, 'rules'], - 'saa': [76489, 'https://srs-f.akamaihd.net', 2036780, 'srs_saa'], - 'smbiz': [76461, 'https://smbiz-f.akamaihd.net', 2036786, 'smallbusiness'], - 'srs': [75229, 'https://srs-f.akamaihd.net', 2031966, 'srs_srs'], - 'uscc': [76487, 'https://srs-f.akamaihd.net', 2036781, 'srs_uscc'], - 'vetaff': [76462, 'https://vetaff-f.akamaihd.net', 2036785, 'veteransaffairs'], - 'arch': [None, 'https://ussenate-f.akamaihd.net/', None, None], - 'uscp': [None, '', 2043685, None, 'uscp'], - 'cio': [None, '', 2043686, None, 'cio'], + 'ag': [76440, 'https://ag-f.akamaihd.net', 2036803, 'agriculture'], + 'aging': [76442, 'https://aging-f.akamaihd.net', 2036801, 'aging'], + 'approps': [76441, 'https://approps-f.akamaihd.net', 2036802, 'appropriations'], + 'armed': [76445, 'https://armed-f.akamaihd.net', 2036800, 'armedservices'], + 'banking': [76446, 'https://banking-f.akamaihd.net', 2036799, 'banking'], + 'budget': [76447, 'https://budget-f.akamaihd.net', 2036798, 'budget'], + 'cecc': [76486, 'https://srs-f.akamaihd.net', 2036782, 'srs_cecc'], + 'commerce': [80177, 'https://commerce1-f.akamaihd.net', 2036779, 'commerce'], + 'csce': [75229, 'https://srs-f.akamaihd.net', 2036777, 'srs_srs'], + 'dpc': [76590, 'https://dpc-f.akamaihd.net', None, 'dpc'], + 'energy': [76448, 'https://energy-f.akamaihd.net', 2036797, 'energy'], + 'epw': [76478, 'https://epw-f.akamaihd.net', 2036783, 'environment'], + 'ethics': [76449, 'https://ethics-f.akamaihd.net', 2036796, 'ethics'], + 'finance': [76450, 'https://finance-f.akamaihd.net', 2036795, 'finance_finance'], + 'foreign': [76451, 'https://foreign-f.akamaihd.net', 2036794, 'foreignrelations'], + 'govtaff': [76453, 'https://govtaff-f.akamaihd.net', 2036792, 'hsgac'], + 'help': [76452, 'https://help-f.akamaihd.net', 2036793, 'help'], + 'indian': [76455, 'https://indian-f.akamaihd.net', 2036791, 'indianaffairs'], + 'intel': [76456, 'https://intel-f.akamaihd.net', 2036790, 'intelligence'], + 'intlnarc': [76457, 'https://intlnarc-f.akamaihd.net', None, 'internationalnarcoticscaucus'], + 'jccic': [85180, 'https://jccic-f.akamaihd.net', 2036778, 'jccic'], + 'jec': [76458, 'https://jec-f.akamaihd.net', 2036789, 'jointeconomic'], + 'judiciary': [76459, 'https://judiciary-f.akamaihd.net', 2036788, 'judiciary'], + 'rpc': [76591, 'https://rpc-f.akamaihd.net', None, 'rpc'], + 'rules': [76460, 'https://rules-f.akamaihd.net', 2036787, 'rules'], + 'saa': [76489, 'https://srs-f.akamaihd.net', 2036780, 'srs_saa'], + 'smbiz': [76461, 'https://smbiz-f.akamaihd.net', 2036786, 'smallbusiness'], + 'srs': [75229, 'https://srs-f.akamaihd.net', 2031966, 'srs_srs'], + 'uscc': [76487, 'https://srs-f.akamaihd.net', 2036781, 'srs_uscc'], + 'vetaff': [76462, 'https://vetaff-f.akamaihd.net', 2036785, 'veteransaffairs'], + 'arch': [None, 'https://ussenate-f.akamaihd.net/', None, None], + 'uscp': [None, '', 2043685, 'uscp'], + 'cio': [None, '', 2043686, 'cio'], } + _IE_NAME = 'senate.gov' _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P.+)' _TESTS = [{ @@ -56,7 +58,7 @@ class SenateISVPIE(InfoExtractor): 'info_dict': { 'id': 'judiciary031715', 'ext': 'mp4', - 'title': 'Integrated Senate Video Player', + 'title': 'judiciary031715', 'thumbnail': r're:^https?://.*\.(?:jpg|png)$', }, 'params': { @@ -69,7 +71,8 @@ class SenateISVPIE(InfoExtractor): 'info_dict': { 'id': 'intel090613', 'ext': 'mp4', - 'title': 'Integrated Senate Video Player' + 'title': 'intel090613', + 'thumbnail': r're:^https?://.*\.(?:jpg|png)$', } }, { # From http://www.c-span.org/video/?96791-1 @@ -78,67 +81,83 @@ class SenateISVPIE(InfoExtractor): }] @staticmethod + # returns url from an iframe def _search_iframe_url(webpage): mobj = re.search( - r"]+src=['\"](?Phttps?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]", + r''']+\bsrc\s*=\s*(['"])(?Phttps?://www\.senate\.gov/isvp/?\?(?:(?!\1)\S)+)''', webpage) if mobj: return mobj.group('url') + # returns stream_number, stream_domain, stream_id, and msl3 def _get_info_for_comm(self, committee): - for entry in self._COMM_MAP: - if entry[0] == committee: - return entry[1:] + return self._COMM_MAP[committee][0:] def _real_extract(self, url): + # smuggled_data may contain a forced title that should be used url, smuggled_data = unsmuggle_url(url, {}) - qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs')) - if not qs.get('filename') or not qs.get('type') or not qs.get('comm'): - raise ExtractorError('Invalid URL', expected=True) - video_id = re.sub(r'.mp4$', '', qs['filename'][0]) + # error handling for invalid URL - specify what + if not qs.get('comm'): + raise ExtractorError('''Invalid URL. Missing committee in query parameters.''', expected=True) + if not qs.get('filename'): + raise ExtractorError('''Invalid URL. Missing filename in query parameters.''', expected=True) - webpage = self._download_webpage(url, video_id) + committee = qs.get('comm')[0] + filename = qs.get('filename')[0] + video_id = re.sub(r'\.mp4$', '', filename) - if smuggled_data.get('force_title'): + # there is no point in pulling the title from the webpage since it always defaults to 'Integrated Senate Player' + title = filename + if smuggled_data: title = smuggled_data['force_title'] - else: - title = self._html_search_regex(r'([^<]+)', webpage, video_id) - poster = qs.get('poster') - thumbnail = poster[0] if poster else None + stream_number, stream_domain, stream_id, msl3 = self._get_info_for_comm(committee) - video_type = qs['type'][0] - committee = video_type if video_type == 'arch' else qs['comm'][0] - stream_num, domain = self._get_info_for_comm(committee) + # the possible locations that the video could be contained at. + possible_manifest_urls = [ + f'https://www-senate-gov-media-srs.akamaized.net/hls/live/{stream_id}/{committee}/{filename}/master.m3u8', + f'https://www-senate-gov-msl3archive.akamaized.net/{msl3}/{filename}_1/master.m3u8', + f'{stream_domain}/i/{filename}_1@{stream_number}/master.m3u8', + f'https://ussenate-f.akamaihd.net/i/{video_id}', + ] + + # we iterate through the possible locations until we find a hit, that is when formats is filled. formats = [] - if video_type == 'arch': - filename = video_id if '.' in video_id else video_id + '.mp4' - formats = [{ - # All parameters in the query string are necessary to prevent a 403 error - 'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=', - }] - else: - hdcore_sign = 'hdcore=3.1.0' - url_params = (domain, video_id, stream_num) - f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign - m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params - for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'): - # URLs without the extra param induce an 404 error - entry.update({'extra_param_to_segment_url': hdcore_sign}) - formats.append(entry) - for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'): - mobj = re.search(r'(?P(?:-p|-b)).m3u8', entry['url']) + for url in possible_manifest_urls: + print('!!!') + entries = self._extract_m3u8_formats( + url, + video_id, + ext='mp4', + m3u8_id='hls', + entry_protocol='m3u8_native', + fatal=False, + ) + print('|-|-|-|') + + for entry in entries: + mobj = re.search(r'(?P-[pb]).m3u8', entry['url']) if mobj: entry['format_id'] += mobj.group('tag') formats.append(entry) - self._sort_formats(formats) + if formats: + break + + self._sort_formats(formats) + thumbnail = url_or_none(qs.get('poster', [None])[-1]) + start_time = parse_duration(qs.get('stt', [None])[-1]) + stop_time = parse_duration(qs.get('dur', [None])[-1]) + if stop_time is not None: + stop_time += start_time or 0 return { 'id': video_id, 'title': title, 'formats': formats, 'thumbnail': thumbnail, - } + 'start_time': start_time, + 'stop_time': stop_time, + } \ No newline at end of file