yt_dlp/extractor/senategov.py

   1 import re
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     parse_qs,
   8     unsmuggle_url,
   9 )
  10
  11 _COMMITTEES = {
  12     'ag': ('76440', 'http://ag-f.akamaihd.net'),
  13     'aging': ('76442', 'http://aging-f.akamaihd.net'),
  14     'approps': ('76441', 'http://approps-f.akamaihd.net'),
  15     'arch': ('', 'http://ussenate-f.akamaihd.net'),
  16     'armed': ('76445', 'http://armed-f.akamaihd.net'),
  17     'banking': ('76446', 'http://banking-f.akamaihd.net'),
  18     'budget': ('76447', 'http://budget-f.akamaihd.net'),
  19     'cecc': ('76486', 'http://srs-f.akamaihd.net'),
  20     'commerce': ('80177', 'http://commerce1-f.akamaihd.net'),
  21     'csce': ('75229', 'http://srs-f.akamaihd.net'),
  22     'dpc': ('76590', 'http://dpc-f.akamaihd.net'),
  23     'energy': ('76448', 'http://energy-f.akamaihd.net'),
  24     'epw': ('76478', 'http://epw-f.akamaihd.net'),
  25     'ethics': ('76449', 'http://ethics-f.akamaihd.net'),
  26     'finance': ('76450', 'http://finance-f.akamaihd.net'),
  27     'foreign': ('76451', 'http://foreign-f.akamaihd.net'),
  28     'govtaff': ('76453', 'http://govtaff-f.akamaihd.net'),
  29     'help': ('76452', 'http://help-f.akamaihd.net'),
  30     'indian': ('76455', 'http://indian-f.akamaihd.net'),
  31     'intel': ('76456', 'http://intel-f.akamaihd.net'),
  32     'intlnarc': ('76457', 'http://intlnarc-f.akamaihd.net'),
  33     'jccic': ('85180', 'http://jccic-f.akamaihd.net'),
  34     'jec': ('76458', 'http://jec-f.akamaihd.net'),
  35     'judiciary': ('76459', 'http://judiciary-f.akamaihd.net'),
  36     'rpc': ('76591', 'http://rpc-f.akamaihd.net'),
  37     'rules': ('76460', 'http://rules-f.akamaihd.net'),
  38     'saa': ('76489', 'http://srs-f.akamaihd.net'),
  39     'smbiz': ('76461', 'http://smbiz-f.akamaihd.net'),
  40     'srs': ('75229', 'http://srs-f.akamaihd.net'),
  41     'uscc': ('76487', 'http://srs-f.akamaihd.net'),
  42     'vetaff': ('76462', 'http://vetaff-f.akamaihd.net'),
  43 }
  44
  45
  46 class SenateISVPIE(InfoExtractor):
  47     _IE_NAME = 'senate.gov:isvp'
  48     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
  49     _EMBED_REGEX = [r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]"]
  50
  51     _TESTS = [{
  52         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
  53         'info_dict': {
  54             'id': 'judiciary031715',
  55             'ext': 'mp4',
  56             'title': 'Integrated Senate Video Player',
  57             'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
  58         },
  59         'params': {
  60             # m3u8 download
  61             'skip_download': True,
  62         },
  63     }, {
  64         'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
  65         'info_dict': {
  66             'id': 'commerce011514',
  67             'ext': 'mp4',
  68             'title': 'Integrated Senate Video Player',
  69         },
  70         'params': {
  71             # m3u8 download
  72             'skip_download': True,
  73         },
  74     }, {
  75         'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
  76         # checksum differs each time
  77         'info_dict': {
  78             'id': 'intel090613',
  79             'ext': 'mp4',
  80             'title': 'Integrated Senate Video Player',
  81         },
  82     }, {
  83         # From http://www.c-span.org/video/?96791-1
  84         'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
  85         'only_matching': True,
  86     }]
  87
  88     def _real_extract(self, url):
  89         url, smuggled_data = unsmuggle_url(url, {})
  90
  91         qs = urllib.parse.parse_qs(self._match_valid_url(url).group('qs'))
  92         if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
  93             raise ExtractorError('Invalid URL', expected=True)
  94
  95         video_id = re.sub(r'.mp4$', '', qs['filename'][0])
  96
  97         webpage = self._download_webpage(url, video_id)
  98
  99         if smuggled_data.get('force_title'):
 100             title = smuggled_data['force_title']
 101         else:
 102             title = self._html_extract_title(webpage)
 103         poster = qs.get('poster')
 104         thumbnail = poster[0] if poster else None
 105
 106         video_type = qs['type'][0]
 107         committee = video_type if video_type == 'arch' else qs['comm'][0]
 108
 109         stream_num, domain = _COMMITTEES[committee]
 110
 111         formats = []
 112         if video_type == 'arch':
 113             filename = video_id if '.' in video_id else video_id + '.mp4'
 114             m3u8_url = urllib.parse.urljoin(domain, 'i/' + filename + '/master.m3u8')
 115             formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8')
 116         else:
 117             hdcore_sign = 'hdcore=3.1.0'
 118             url_params = (domain, video_id, stream_num)
 119             f4m_url = f'%s/z/%s_1@%s/manifest.f4m?{hdcore_sign}' % url_params
 120             m3u8_url = '{}/i/{}_1@{}/master.m3u8'.format(*url_params)
 121             for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
 122                 # URLs without the extra param induce an 404 error
 123                 entry.update({'extra_param_to_segment_url': hdcore_sign})
 124                 formats.append(entry)
 125             for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
 126                 mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
 127                 if mobj:
 128                     entry['format_id'] += mobj.group('tag')
 129                 formats.append(entry)
 130
 131         return {
 132             'id': video_id,
 133             'title': title,
 134             'formats': formats,
 135             'thumbnail': thumbnail,
 136         }
 137
 138
 139 class SenateGovIE(InfoExtractor):
 140     _IE_NAME = 'senate.gov'
 141     _VALID_URL = r'https?:\/\/(?:www\.)?(help|appropriations|judiciary|banking|armed-services|finance)\.senate\.gov'
 142     _TESTS = [{
 143         'url': 'https://www.help.senate.gov/hearings/vaccines-saving-lives-ensuring-confidence-and-protecting-public-health',
 144         'info_dict': {
 145             'id': 'help090920',
 146             'display_id': 'vaccines-saving-lives-ensuring-confidence-and-protecting-public-health',
 147             'title': 'Vaccines: Saving Lives, Ensuring Confidence, and Protecting Public Health',
 148             'description': 'The U.S. Senate Committee on Health, Education, Labor & Pensions',
 149             'ext': 'mp4',
 150         },
 151         'params': {'skip_download': 'm3u8'},
 152     }, {
 153         'url': 'https://www.appropriations.senate.gov/hearings/watch?hearingid=B8A25434-5056-A066-6020-1F68CB75F0CD',
 154         'info_dict': {
 155             'id': 'appropsA051518',
 156             'display_id': 'watch?hearingid=B8A25434-5056-A066-6020-1F68CB75F0CD',
 157             'title': 'Review of the FY2019 Budget Request for the U.S. Army',
 158             'ext': 'mp4',
 159         },
 160         'params': {'skip_download': 'm3u8'},
 161     }, {
 162         'url': 'https://www.banking.senate.gov/hearings/21st-century-communities-public-transportation-infrastructure-investment-and-fast-act-reauthorization',
 163         'info_dict': {
 164             'id': 'banking041521',
 165             'display_id': '21st-century-communities-public-transportation-infrastructure-investment-and-fast-act-reauthorization',
 166             'title': '21st Century Communities: Public Transportation Infrastructure Investment and FAST Act Reauthorization',
 167             'description': 'The Official website of The United States Committee on Banking, Housing, and Urban Affairs',
 168             'ext': 'mp4',
 169         },
 170         'params': {'skip_download': 'm3u8'},
 171     }]
 172
 173     def _real_extract(self, url):
 174         display_id = self._generic_id(url)
 175         webpage = self._download_webpage(url, display_id)
 176         parse_info = parse_qs(self._search_regex(
 177             r'<iframe class="[^>"]*streaminghearing[^>"]*"\s[^>]*\bsrc="([^">]*)', webpage, 'hearing URL'))
 178
 179         stream_num, stream_domain = _COMMITTEES[parse_info['comm'][-1]]
 180         filename = parse_info['filename'][-1]
 181
 182         formats = self._extract_m3u8_formats(
 183             f'{stream_domain}/i/{filename}_1@{stream_num}/master.m3u8',
 184             display_id, ext='mp4')
 185
 186         title = self._html_search_regex(
 187             (*self._og_regexes('title'), r'(?s)<title>([^<]*?)</title>'), webpage, 'video title')
 188
 189         return {
 190             'id': re.sub(r'.mp4$', '', filename),
 191             'display_id': display_id,
 192             'title': re.sub(r'\s+', ' ', title.split('|')[0]).strip(),
 193             'description': self._og_search_description(webpage, default=None),
 194             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 195             'age_limit': self._rta_search(webpage),
 196             'formats': formats,
 197         }