From d59b83f04be9b3cb727242b85380b361c5752838 Mon Sep 17 00:00:00 2001 From: jsmnhou Date: Sun, 9 Apr 2023 16:10:06 -0400 Subject: [PATCH 1/8] Updated _real_extract() to iterate through possible manifest URLs to find the m3u8. Added start_time and stop_time metadata. --- youtube_dl/extractor/senateisvp.py | 87 +++++++++++++++++------------- 1 file changed, 51 insertions(+), 36 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index db5ef8b57..351f076db 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -5,7 +5,9 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, + parse_duration, unsmuggle_url, + url_or_none, ) from ..compat import ( compat_parse_qs, @@ -87,67 +89,80 @@ 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, 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$', '', qs['filename'][0]) + # error handling for invalid URL - specify which error + if not qs.get('filename'): + raise ExtractorError('Invalid URL. Missing filename in query parameters', expected=True) + if not qs.get('comm'): + raise ExtractorError('Invalid URL. Missing committee in query parameters', expected=True) - webpage = self._download_webpage(url, video_id) + committee = qs.get('comm')[0] + filename = qs.get('filename')[0] + video_id = re.sub(r'\.mp4$', '', filename) - if smuggled_data.get('force_title'): - 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 + # there is no point in pulling the title from the webpage since it always defaults to 'Integrated Senate Player' + title = smuggled_data.get('force_title') or filename - 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) + # extract more info about committee (for matching to possible locations) + stream_number, stream_domain, stream_id, msl3 = self._get_info_for_comm(committee) + # possible locations that m3u8 could be located at + possible_manifest_urls = [ + 'https://www-senate-gov-media-srs.akamaized.net/hls/live/%d/%s/%s/master.m3u8' % (stream_id, committee, filename), + 'https://www-senate-gov-msl3archive.akamaized.net/%s/%s_1/master.m3u8' % (msl3, filename), + '{stream_domain}/i/%s_1@%d/master.m3u8' % (filename, stream_number), + 'https://ussenate-f.akamaihd.net/i/%s' % video_id, + ] + + # iterate through possible locations until we find a match (match found 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: + entries = self._extract_m3u8_formats( + url, + video_id, + ext='mp4', + m3u8_id='hls', + entry_protocal='mu38_native', + fatal=False + ) + + 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, } From 7def329f19a6ff20fdb6667cd403c51919ad8335 Mon Sep 17 00:00:00 2001 From: jsmnhou Date: Sun, 9 Apr 2023 16:13:13 -0400 Subject: [PATCH 2/8] Updated _COMM_MAP to be a dictionary to speed up execution. Updated values from latest senate.gov page. --- youtube_dl/extractor/senateisvp.py | 70 ++++++++++++++++-------------- 1 file changed, 37 insertions(+), 33 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index 351f076db..f58bd39b3 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -16,39 +16,43 @@ from ..compat import ( class SenateISVPIE(InfoExtractor): - _COMM_MAP = [ - ['ag', '76440', 'http://ag-f.akamaihd.net'], - ['aging', '76442', 'http://aging-f.akamaihd.net'], - ['approps', '76441', 'http://approps-f.akamaihd.net'], - ['armed', '76445', 'http://armed-f.akamaihd.net'], - ['banking', '76446', 'http://banking-f.akamaihd.net'], - ['budget', '76447', 'http://budget-f.akamaihd.net'], - ['cecc', '76486', 'http://srs-f.akamaihd.net'], - ['commerce', '80177', 'http://commerce1-f.akamaihd.net'], - ['csce', '75229', 'http://srs-f.akamaihd.net'], - ['dpc', '76590', 'http://dpc-f.akamaihd.net'], - ['energy', '76448', 'http://energy-f.akamaihd.net'], - ['epw', '76478', 'http://epw-f.akamaihd.net'], - ['ethics', '76449', 'http://ethics-f.akamaihd.net'], - ['finance', '76450', 'http://finance-f.akamaihd.net'], - ['foreign', '76451', 'http://foreign-f.akamaihd.net'], - ['govtaff', '76453', 'http://govtaff-f.akamaihd.net'], - ['help', '76452', 'http://help-f.akamaihd.net'], - ['indian', '76455', 'http://indian-f.akamaihd.net'], - ['intel', '76456', 'http://intel-f.akamaihd.net'], - ['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net'], - ['jccic', '85180', 'http://jccic-f.akamaihd.net'], - ['jec', '76458', 'http://jec-f.akamaihd.net'], - ['judiciary', '76459', 'http://judiciary-f.akamaihd.net'], - ['rpc', '76591', 'http://rpc-f.akamaihd.net'], - ['rules', '76460', 'http://rules-f.akamaihd.net'], - ['saa', '76489', 'http://srs-f.akamaihd.net'], - ['smbiz', '76461', 'http://smbiz-f.akamaihd.net'], - ['srs', '75229', 'http://srs-f.akamaihd.net'], - ['uscc', '76487', 'http://srs-f.akamaihd.net'], - ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'], - ['arch', '', 'http://ussenate-f.akamaihd.net/'] - ] + # 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, 'uscp'], + 'cio': [None, '', 2043686, 'cio'], + } + _IE_NAME = 'senate.gov' _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P.+)' _TESTS = [{ From 2fcb8b8c2096e37a3620391584280a77faba0b9f Mon Sep 17 00:00:00 2001 From: jsmnhou Date: Sun, 9 Apr 2023 16:17:55 -0400 Subject: [PATCH 3/8] Added new tests and added expected warnings to existing tests. --- youtube_dl/extractor/senateisvp.py | 54 +++++++++++++++++------------- 1 file changed, 30 insertions(+), 24 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index f58bd39b3..d3afc4858 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -60,36 +60,42 @@ class SenateISVPIE(InfoExtractor): 'info_dict': { 'id': 'judiciary031715', 'ext': 'mp4', - 'title': 'Integrated Senate Video Player', - 'thumbnail': r're:^https?://.*\.(?:jpg|png)$', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, { - 'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false', - 'info_dict': { - 'id': 'commerce011514', - 'ext': 'mp4', - 'title': 'Integrated Senate Video Player' - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'title': 'judiciary031715', + 'thumbnail': 'http://www.judiciary.senate.gov/themes/judiciary/images/video-poster-flash-fit.png', }, + 'expected_warnings': ['Failed to download m3u8 information: HTTP Error 404: Not Found'], }, { 'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi', - # checksum differs each time 'info_dict': { 'id': 'intel090613', 'ext': 'mp4', - 'title': 'Integrated Senate Video Player' - } + 'title': 'intel090613', + }, + 'expected_warnings': ['Failed to download m3u8 information: HTTP Error 404: Not Found'], }, { - # From http://www.c-span.org/video/?96791-1 - 'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715', - 'only_matching': True, + 'url': 'https://www.senate.gov/isvp/?comm=govtaff&type=archv&stt=975&filename=govtaff111722&auto_play=false&poster=https%3A%2F%2Fwww%2Ehsgac%2Esenate%2Egov%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng', + 'info_dict': { + 'id': 'govtaff111722', + 'ext': 'mp4', + 'title': 'govtaff111722', + 'thumbnail': 'https://www.hsgac.senate.gov/images/video-poster-flash-fit.png', + }, + }, { + 'url': 'https://www.senate.gov/isvp/?type=arch&comm=energy&filename=energy111722&stt=00:22:30&auto_play=false&wmode=transparent&poster=https%3A%2F%2Fwww%2Eenergy%2Esenate%2Egov%2Fthemes%2Fenergy%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng', + 'info_dict': { + 'id': 'energy111722', + 'ext': 'mp4', + 'title': 'energy111722', + 'thumbnail': 'https://www.energy.senate.gov/themes/energy/images/video-poster-flash-fit.png', + }, + }, { + 'url': 'https://www.senate.gov/isvp/?comm=foreign&type=archv&stt=0&filename=foreign080322&auto_play=false&wmode=transparent&poster=https%3A%2F%2Fwww%2Eforeign%2Esenate%2Egov%2Fthemes%2Fforeign%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng', + 'info_dict': { + 'id': 'foreign080322', + 'ext': 'mp4', + 'title': 'foreign080322', + 'thumbnail': 'https://www.foreign.senate.gov/themes/foreign/images/video-poster-flash-fit.png', + }, }] @staticmethod @@ -142,7 +148,7 @@ class SenateISVPIE(InfoExtractor): video_id, ext='mp4', m3u8_id='hls', - entry_protocal='mu38_native', + entry_protocol='mu38_native', fatal=False ) From f5e01562b1dc6f0fdfdd20a2e15861f5365de0e7 Mon Sep 17 00:00:00 2001 From: jsmnhou Date: Sun, 9 Apr 2023 16:23:01 -0400 Subject: [PATCH 4/8] Condensed code when extracting formats. Edited comments. --- youtube_dl/extractor/senateisvp.py | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index d3afc4858..0d42872c4 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -132,7 +132,7 @@ class SenateISVPIE(InfoExtractor): # extract more info about committee (for matching to possible locations) stream_number, stream_domain, stream_id, msl3 = self._get_info_for_comm(committee) - # possible locations that m3u8 could be located at + # the possible locations for the video: only the first has been seen in use possible_manifest_urls = [ 'https://www-senate-gov-media-srs.akamaized.net/hls/live/%d/%s/%s/master.m3u8' % (stream_id, committee, filename), 'https://www-senate-gov-msl3archive.akamaized.net/%s/%s_1/master.m3u8' % (msl3, filename), @@ -140,17 +140,12 @@ class SenateISVPIE(InfoExtractor): 'https://ussenate-f.akamaihd.net/i/%s' % video_id, ] - # iterate through possible locations until we find a match (match found when formats is filled) + # we iterate through the possible locations until we find formats formats = [] for url in possible_manifest_urls: entries = self._extract_m3u8_formats( - url, - video_id, - ext='mp4', - m3u8_id='hls', - entry_protocol='mu38_native', - fatal=False - ) + url, video_id, ext='mp4', m3u8_id='hls', + entry_protocol='m3u8_native', fatal=False) for entry in entries: mobj = re.search(r'(?P-[pb]).m3u8', entry['url']) From 6d1af4e2cff2bc2cf631cab29ced7053a5a58f7a Mon Sep 17 00:00:00 2001 From: jsmnhou Date: Mon, 10 Apr 2023 20:24:02 -0400 Subject: [PATCH 5/8] Changed _COMM_MAP to original format and added __dictify to be able to process dict-ified format. --- youtube_dl/extractor/senateisvp.py | 114 ++++++++++++++++++++--------- 1 file changed, 78 insertions(+), 36 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index 0d42872c4..d085fa792 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -17,41 +17,78 @@ from ..compat import ( 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, 'uscp'], - 'cio': [None, '', 2043686, 'cio'], - } + # _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, 'uscp'], + # 'cio': [None, '', 2043686, 'cio'], + # } + + # [committee, stream_number, stream_domain, stream_id, msl3] + _COMM_MAP = [ + ['ag', '76440', 'http://ag-f.akamaihd.net', '2036803', 'agriculture'], + ['aging', '76442', 'http://aging-f.akamaihd.net', '2036801', 'aging'], + ['approps', '76441', 'http://approps-f.akamaihd.net', '2036802', 'appropriations'], + ['armed', '76445', 'http://armed-f.akamaihd.net', '2036800', 'armedservices'], + ['banking', '76446', 'http://banking-f.akamaihd.net', '2036799', 'banking'], + ['budget', '76447', 'http://budget-f.akamaihd.net', '2036798', 'budget'], + ['cecc', '76486', 'http://srs-f.akamaihd.net', '2036782', 'srs_cecc'], + ['commerce', '80177', 'http://commerce1-f.akamaihd.net', '2036779', 'commerce'], + ['csce', '75229', 'http://srs-f.akamaihd.net', '2036777', 'srs_srs'], + ['dpc', '76590', 'http://dpc-f.akamaihd.net', None, 'dpc'], + ['energy', '76448', 'http://energy-f.akamaihd.net', '2036797', 'energy'], + ['epw', '76478', 'http://epw-f.akamaihd.net', '2036783', 'environment'], + ['ethics', '76449', 'http://ethics-f.akamaihd.net', '2036796', 'ethics'], + ['finance', '76450', 'http://finance-f.akamaihd.net', '2036795', 'finance_finance'], + ['foreign', '76451', 'http://foreign-f.akamaihd.net', '2036794', 'foreignrelations'], + ['govtaff', '76453', 'http://govtaff-f.akamaihd.net', '2036792', 'hsgac'], + ['help', '76452', 'http://help-f.akamaihd.net', '2036793', 'help'], + ['indian', '76455', 'http://indian-f.akamaihd.net', '2036791', 'indianaffairs'], + ['intel', '76456', 'http://intel-f.akamaihd.net', '2036790', 'intelligence'], + ['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net', None, 'internationalnarcoticscaucus'], + ['jccic', '85180', 'http://jccic-f.akamaihd.net', '2036778', 'jccic'], + ['jec', '76458', 'http://jec-f.akamaihd.net', '2036789', 'jointeconomic'], + ['judiciary', '76459', 'http://judiciary-f.akamaihd.net', '2036788', 'judiciary'], + ['rpc', '76591', 'http://rpc-f.akamaihd.net', None, 'rpc'], + ['rules', '76460', 'http://rules-f.akamaihd.net', '2036787', 'rules'], + ['saa', '76489', 'http://srs-f.akamaihd.net', '2036780', 'srs_saa'], + ['smbiz', '76461', 'http://smbiz-f.akamaihd.net', '2036786', 'smallbusiness'], + ['srs', '75229', 'http://srs-f.akamaihd.net', '2031966', 'srs_srs'], + ['uscc', '76487', 'http://srs-f.akamaihd.net', '2036781', 'srs_uscc'], + ['vetaff', '76462', 'http://vetaff-f.akamaihd.net', '2036785', 'veteransaffairs'], + ['arch', '', 'http://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.+)' @@ -109,7 +146,12 @@ class SenateISVPIE(InfoExtractor): # returns stream_number, stream_domain, stream_id, msl3 def _get_info_for_comm(self, committee): - return self._COMM_MAP[committee][0:] + # return self._COMM_MAP[committee][0:] + return self.__dictify(committee) + + @staticmethod + def __dictify(cm): + return dict((row[0], (row[1:] + ['', ''])[:4]) for row in cm) def _real_extract(self, url): # smuggled data may contain a forced title that should be used From e1b7640587c420cad3939162b91afc0e49eb6b79 Mon Sep 17 00:00:00 2001 From: jsmnhou Date: Mon, 10 Apr 2023 20:31:22 -0400 Subject: [PATCH 6/8] Changes to possible manifest urls. --- youtube_dl/extractor/senateisvp.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index d085fa792..8970acb10 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -178,8 +178,8 @@ class SenateISVPIE(InfoExtractor): possible_manifest_urls = [ 'https://www-senate-gov-media-srs.akamaized.net/hls/live/%d/%s/%s/master.m3u8' % (stream_id, committee, filename), 'https://www-senate-gov-msl3archive.akamaized.net/%s/%s_1/master.m3u8' % (msl3, filename), - '{stream_domain}/i/%s_1@%d/master.m3u8' % (filename, stream_number), - 'https://ussenate-f.akamaihd.net/i/%s' % video_id, + '%s/i/%s_1@%d/master.m3u8' % (stream_domain, filename, stream_number), + 'https://ussenate-f.akamaihd.net/i/%s.mp4/master.m3u8' % video_id, ] # we iterate through the possible locations until we find formats From df617513cc049ca1a3a7bdb7ff6078a52975db96 Mon Sep 17 00:00:00 2001 From: jsmnhou Date: Mon, 10 Apr 2023 21:05:31 -0400 Subject: [PATCH 7/8] Fixed __dictify to support new array format. --- youtube_dl/extractor/senateisvp.py | 63 +++++++----------------------- 1 file changed, 14 insertions(+), 49 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index 8970acb10..4a11aafe9 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -16,43 +16,7 @@ from ..compat import ( 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, 'uscp'], - # 'cio': [None, '', 2043686, 'cio'], - # } - + # [committee, stream_number, stream_domain, stream_id, msl3] _COMM_MAP = [ ['ag', '76440', 'http://ag-f.akamaihd.net', '2036803', 'agriculture'], @@ -85,8 +49,8 @@ class SenateISVPIE(InfoExtractor): ['srs', '75229', 'http://srs-f.akamaihd.net', '2031966', 'srs_srs'], ['uscc', '76487', 'http://srs-f.akamaihd.net', '2036781', 'srs_uscc'], ['vetaff', '76462', 'http://vetaff-f.akamaihd.net', '2036785', 'veteransaffairs'], - ['arch', '', 'http://ussenate-f.akamaihd.net/', None, None] - ['uscp', None, '', '2043685', 'uscp'] + ['arch', '', 'http://ussenate-f.akamaihd.net/', None, None], + ['uscp', None, '', '2043685', 'uscp'], ['cio', None, '', '2043686', 'cio'] ] @@ -136,7 +100,7 @@ class SenateISVPIE(InfoExtractor): }] @staticmethod - #returns url from an iframe + # returns url from an iframe def _search_iframe_url(webpage): mobj = re.search( r''']+\bsrc\s*=\s*(['"])(?Phttps?://www\.senate\.gov/isvp/?\?(?:(?!\1)\S)+)''', @@ -144,15 +108,15 @@ class SenateISVPIE(InfoExtractor): if mobj: return mobj.group('url') - # returns stream_number, stream_domain, stream_id, msl3 - def _get_info_for_comm(self, committee): - # return self._COMM_MAP[committee][0:] - return self.__dictify(committee) - @staticmethod def __dictify(cm): return dict((row[0], (row[1:] + ['', ''])[:4]) for row in cm) + # returns stream_number, stream_domain, stream_id, msl3 + def _get_info_for_comm(self, committee): + dict = self.__dictify(self._COMM_MAP) + return dict[committee][0:] + def _real_extract(self, url): # smuggled data may contain a forced title that should be used url, smuggled_data = unsmuggle_url(url, {}) @@ -171,8 +135,9 @@ class SenateISVPIE(InfoExtractor): # there is no point in pulling the title from the webpage since it always defaults to 'Integrated Senate Player' title = smuggled_data.get('force_title') or filename - # extract more info about committee (for matching to possible locations) stream_number, stream_domain, stream_id, msl3 = self._get_info_for_comm(committee) + stream_number = int(stream_number) + stream_id = int(stream_id) # the possible locations for the video: only the first has been seen in use possible_manifest_urls = [ @@ -182,9 +147,9 @@ class SenateISVPIE(InfoExtractor): 'https://ussenate-f.akamaihd.net/i/%s.mp4/master.m3u8' % video_id, ] - # we iterate through the possible locations until we find formats + # we iterate through the possible locations until we find formats formats = [] - for url in possible_manifest_urls: + for url in possible_manifest_urls: entries = self._extract_m3u8_formats( url, video_id, ext='mp4', m3u8_id='hls', entry_protocol='m3u8_native', fatal=False) @@ -197,7 +162,7 @@ class SenateISVPIE(InfoExtractor): 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]) From 5aee29b7ca489428ca129a89b09a3a0390740466 Mon Sep 17 00:00:00 2001 From: jsmnhou Date: Mon, 10 Apr 2023 21:11:29 -0400 Subject: [PATCH 8/8] Fixed styling to comply with flake8. --- youtube_dl/extractor/senateisvp.py | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index 4a11aafe9..0ba1dae7d 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -9,10 +9,7 @@ from ..utils import ( unsmuggle_url, url_or_none, ) -from ..compat import ( - compat_parse_qs, - compat_urlparse, -) +from ..compat import compat_parse_qs class SenateISVPIE(InfoExtractor):