yt_dlp/extractor/senategov.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_parse_qs,
   6     compat_urlparse,
   7 )
   8 from ..utils import (
   9     ExtractorError,
  10     parse_qs,
  11     unsmuggle_url,
  12 )
  13
  14 _COMMITTEES = {
  15     'ag': ('76440', 'http://ag-f.akamaihd.net'),
  16     'aging': ('76442', 'http://aging-f.akamaihd.net'),
  17     'approps': ('76441', 'http://approps-f.akamaihd.net'),
  18     'arch': ('', 'http://ussenate-f.akamaihd.net'),
  19     'armed': ('76445', 'http://armed-f.akamaihd.net'),
  20     'banking': ('76446', 'http://banking-f.akamaihd.net'),
  21     'budget': ('76447', 'http://budget-f.akamaihd.net'),
  22     'cecc': ('76486', 'http://srs-f.akamaihd.net'),
  23     'commerce': ('80177', 'http://commerce1-f.akamaihd.net'),
  24     'csce': ('75229', 'http://srs-f.akamaihd.net'),
  25     'dpc': ('76590', 'http://dpc-f.akamaihd.net'),
  26     'energy': ('76448', 'http://energy-f.akamaihd.net'),
  27     'epw': ('76478', 'http://epw-f.akamaihd.net'),
  28     'ethics': ('76449', 'http://ethics-f.akamaihd.net'),
  29     'finance': ('76450', 'http://finance-f.akamaihd.net'),
  30     'foreign': ('76451', 'http://foreign-f.akamaihd.net'),
  31     'govtaff': ('76453', 'http://govtaff-f.akamaihd.net'),
  32     'help': ('76452', 'http://help-f.akamaihd.net'),
  33     'indian': ('76455', 'http://indian-f.akamaihd.net'),
  34     'intel': ('76456', 'http://intel-f.akamaihd.net'),
  35     'intlnarc': ('76457', 'http://intlnarc-f.akamaihd.net'),
  36     'jccic': ('85180', 'http://jccic-f.akamaihd.net'),
  37     'jec': ('76458', 'http://jec-f.akamaihd.net'),
  38     'judiciary': ('76459', 'http://judiciary-f.akamaihd.net'),
  39     'rpc': ('76591', 'http://rpc-f.akamaihd.net'),
  40     'rules': ('76460', 'http://rules-f.akamaihd.net'),
  41     'saa': ('76489', 'http://srs-f.akamaihd.net'),
  42     'smbiz': ('76461', 'http://smbiz-f.akamaihd.net'),
  43     'srs': ('75229', 'http://srs-f.akamaihd.net'),
  44     'uscc': ('76487', 'http://srs-f.akamaihd.net'),
  45     'vetaff': ('76462', 'http://vetaff-f.akamaihd.net'),
  46 }
  47
  48
  49 class SenateISVPIE(InfoExtractor):
  50     _IE_NAME = 'senate.gov:isvp'
  51     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
  52
  53     _TESTS = [{
  54         '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',
  55         'info_dict': {
  56             'id': 'judiciary031715',
  57             'ext': 'mp4',
  58             'title': 'Integrated Senate Video Player',
  59             'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
  60         },
  61         'params': {
  62             # m3u8 download
  63             'skip_download': True,
  64         },
  65     }, {
  66         'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
  67         'info_dict': {
  68             'id': 'commerce011514',
  69             'ext': 'mp4',
  70             'title': 'Integrated Senate Video Player'
  71         },
  72         'params': {
  73             # m3u8 download
  74             'skip_download': True,
  75         },
  76     }, {
  77         'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
  78         # checksum differs each time
  79         'info_dict': {
  80             'id': 'intel090613',
  81             'ext': 'mp4',
  82             'title': 'Integrated Senate Video Player'
  83         }
  84     }, {
  85         # From http://www.c-span.org/video/?96791-1
  86         'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
  87         'only_matching': True,
  88     }]
  89
  90     @staticmethod
  91     def _search_iframe_url(webpage):
  92         mobj = re.search(
  93             r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
  94             webpage)
  95         if mobj:
  96             return mobj.group('url')
  97
  98     def _real_extract(self, url):
  99         url, smuggled_data = unsmuggle_url(url, {})
 100
 101         qs = compat_parse_qs(self._match_valid_url(url).group('qs'))
 102         if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
 103             raise ExtractorError('Invalid URL', expected=True)
 104
 105         video_id = re.sub(r'.mp4$', '', qs['filename'][0])
 106
 107         webpage = self._download_webpage(url, video_id)
 108
 109         if smuggled_data.get('force_title'):
 110             title = smuggled_data['force_title']
 111         else:
 112             title = self._html_extract_title(webpage)
 113         poster = qs.get('poster')
 114         thumbnail = poster[0] if poster else None
 115
 116         video_type = qs['type'][0]
 117         committee = video_type if video_type == 'arch' else qs['comm'][0]
 118
 119         stream_num, domain = _COMMITTEES[committee]
 120
 121         formats = []
 122         if video_type == 'arch':
 123             filename = video_id if '.' in video_id else video_id + '.mp4'
 124             m3u8_url = compat_urlparse.urljoin(domain, 'i/' + filename + '/master.m3u8')
 125             formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8')
 126         else:
 127             hdcore_sign = 'hdcore=3.1.0'
 128             url_params = (domain, video_id, stream_num)
 129             f4m_url = f'%s/z/%s_1@%s/manifest.f4m?{hdcore_sign}' % url_params
 130             m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
 131             for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
 132                 # URLs without the extra param induce an 404 error
 133                 entry.update({'extra_param_to_segment_url': hdcore_sign})
 134                 formats.append(entry)
 135             for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
 136                 mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
 137                 if mobj:
 138                     entry['format_id'] += mobj.group('tag')
 139                 formats.append(entry)
 140
 141             self._sort_formats(formats)
 142
 143         return {
 144             'id': video_id,
 145             'title': title,
 146             'formats': formats,
 147             'thumbnail': thumbnail,
 148         }
 149
 150
 151 class SenateGovIE(InfoExtractor):
 152     _IE_NAME = 'senate.gov'
 153     _VALID_URL = r'https?:\/\/(?:www\.)?(help|appropriations|judiciary|banking|armed-services|finance)\.senate\.gov'
 154     _TESTS = [{
 155         'url': 'https://www.help.senate.gov/hearings/vaccines-saving-lives-ensuring-confidence-and-protecting-public-health',
 156         'info_dict': {
 157             'id': 'help090920',
 158             'display_id': 'vaccines-saving-lives-ensuring-confidence-and-protecting-public-health',
 159             'title': 'Vaccines: Saving Lives, Ensuring Confidence, and Protecting Public Health',
 160             'description': 'The U.S. Senate Committee on Health, Education, Labor & Pensions',
 161             'ext': 'mp4',
 162         },
 163         'params': {'skip_download': 'm3u8'},
 164     }, {
 165         'url': 'https://www.appropriations.senate.gov/hearings/watch?hearingid=B8A25434-5056-A066-6020-1F68CB75F0CD',
 166         'info_dict': {
 167             'id': 'appropsA051518',
 168             'display_id': 'watch?hearingid=B8A25434-5056-A066-6020-1F68CB75F0CD',
 169             'title': 'Review of the FY2019 Budget Request for the U.S. Army',
 170             'ext': 'mp4',
 171         },
 172         'params': {'skip_download': 'm3u8'},
 173     }, {
 174         'url': 'https://www.banking.senate.gov/hearings/21st-century-communities-public-transportation-infrastructure-investment-and-fast-act-reauthorization',
 175         'info_dict': {
 176             'id': 'banking041521',
 177             'display_id': '21st-century-communities-public-transportation-infrastructure-investment-and-fast-act-reauthorization',
 178             'title': '21st Century Communities: Public Transportation Infrastructure Investment and FAST Act Reauthorization',
 179             'description': 'The Official website of The United States Committee on Banking, Housing, and Urban Affairs',
 180             'ext': 'mp4',
 181         },
 182         'params': {'skip_download': 'm3u8'},
 183     }]
 184
 185     def _real_extract(self, url):
 186         display_id = self._generic_id(url)
 187         webpage = self._download_webpage(url, display_id)
 188         parse_info = parse_qs(self._search_regex(
 189             r'<iframe class="[^>"]*streaminghearing[^>"]*"\s[^>]*\bsrc="([^">]*)', webpage, 'hearing URL'))
 190
 191         stream_num, stream_domain = _COMMITTEES[parse_info['comm'][-1]]
 192         filename = parse_info['filename'][-1]
 193
 194         formats = self._extract_m3u8_formats(
 195             f'{stream_domain}/i/{filename}_1@{stream_num}/master.m3u8',
 196             display_id, ext='mp4')
 197         self._sort_formats(formats)
 198
 199         title = self._html_search_regex(
 200             (*self._og_regexes('title'), r'(?s)<title>([^<]*?)</title>'), webpage, 'video title')
 201
 202         return {
 203             'id': re.sub(r'.mp4$', '', filename),
 204             'display_id': display_id,
 205             'title': re.sub(r'\s+', ' ', title.split('|')[0]).strip(),
 206             'description': self._og_search_description(webpage, default=None),
 207             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 208             'age_limit': self._rta_search(webpage),
 209             'formats': formats
 210         }