Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/senateisvp.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     unsmuggle_url,
   9 )
  10 from ..compat import (
  11     compat_parse_qs,
  12     compat_urlparse,
  13 )
  14
  15
  16 class SenateISVPIE(InfoExtractor):
  17     _COMM_MAP = [
  18         ["ag", "76440", "http://ag-f.akamaihd.net"],
  19         ["aging", "76442", "http://aging-f.akamaihd.net"],
  20         ["approps", "76441", "http://approps-f.akamaihd.net"],
  21         ["armed", "76445", "http://armed-f.akamaihd.net"],
  22         ["banking", "76446", "http://banking-f.akamaihd.net"],
  23         ["budget", "76447", "http://budget-f.akamaihd.net"],
  24         ["cecc", "76486", "http://srs-f.akamaihd.net"],
  25         ["commerce", "80177", "http://commerce1-f.akamaihd.net"],
  26         ["csce", "75229", "http://srs-f.akamaihd.net"],
  27         ["dpc", "76590", "http://dpc-f.akamaihd.net"],
  28         ["energy", "76448", "http://energy-f.akamaihd.net"],
  29         ["epw", "76478", "http://epw-f.akamaihd.net"],
  30         ["ethics", "76449", "http://ethics-f.akamaihd.net"],
  31         ["finance", "76450", "http://finance-f.akamaihd.net"],
  32         ["foreign", "76451", "http://foreign-f.akamaihd.net"],
  33         ["govtaff", "76453", "http://govtaff-f.akamaihd.net"],
  34         ["help", "76452", "http://help-f.akamaihd.net"],
  35         ["indian", "76455", "http://indian-f.akamaihd.net"],
  36         ["intel", "76456", "http://intel-f.akamaihd.net"],
  37         ["intlnarc", "76457", "http://intlnarc-f.akamaihd.net"],
  38         ["jccic", "85180", "http://jccic-f.akamaihd.net"],
  39         ["jec", "76458", "http://jec-f.akamaihd.net"],
  40         ["judiciary", "76459", "http://judiciary-f.akamaihd.net"],
  41         ["rpc", "76591", "http://rpc-f.akamaihd.net"],
  42         ["rules", "76460", "http://rules-f.akamaihd.net"],
  43         ["saa", "76489", "http://srs-f.akamaihd.net"],
  44         ["smbiz", "76461", "http://smbiz-f.akamaihd.net"],
  45         ["srs", "75229", "http://srs-f.akamaihd.net"],
  46         ["uscc", "76487", "http://srs-f.akamaihd.net"],
  47         ["vetaff", "76462", "http://vetaff-f.akamaihd.net"],
  48         ["arch", "", "http://ussenate-f.akamaihd.net/"]
  49     ]
  50     _IE_NAME = 'senate.gov'
  51     _VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P<qs>.+)'
  52     _TESTS = [{
  53         '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',
  54         'info_dict': {
  55             'id': 'judiciary031715',
  56             'ext': 'flv',
  57             'title': 'Integrated Senate Video Player',
  58             'thumbnail': 're:^https?://.*\.(?:jpg|png)$',
  59         }
  60     }, {
  61         'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
  62         'info_dict': {
  63             'id': 'commerce011514',
  64             'ext': 'flv',
  65             'title': 'Integrated Senate Video Player'
  66         }
  67     }, {
  68         'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
  69         # checksum differs each time
  70         'info_dict': {
  71             'id': 'intel090613',
  72             'ext': 'mp4',
  73             'title': 'Integrated Senate Video Player'
  74         }
  75     }]
  76
  77     @staticmethod
  78     def _search_iframe_url(webpage):
  79         mobj = re.search(
  80             r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/\?[^'\"]+)['\"]",
  81             webpage)
  82         if mobj:
  83             return mobj.group('url')
  84
  85     def _get_info_for_comm(self, committee):
  86         for entry in self._COMM_MAP:
  87             if entry[0] == committee:
  88                 return entry[1:]
  89
  90     def _real_extract(self, url):
  91         url, smuggled_data = unsmuggle_url(url, {})
  92
  93         qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
  94         if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
  95             raise ExtractorError('Invalid URL', expected=True)
  96
  97         video_id = re.sub(r'.mp4$', '', qs['filename'][0])
  98
  99         webpage = self._download_webpage(url, video_id)
 100
 101         if smuggled_data.get('force_title'):
 102             title = smuggled_data['force_title']
 103         else:
 104             title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
 105         poster = qs.get('poster')
 106         thumbnail = poster[0] if poster else None
 107
 108         video_type = qs['type'][0]
 109         committee = video_type if video_type == 'arch' else qs['comm'][0]
 110         stream_num, domain = self._get_info_for_comm(committee)
 111
 112         formats = []
 113         if video_type == 'arch':
 114             filename = video_id if '.' in video_id else video_id + '.mp4'
 115             formats = [{
 116                 # All parameters in the query string are necessary to prevent a 403 error
 117                 'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
 118             }]
 119         else:
 120             hdcore_sign = '?hdcore=3.1.0'
 121             url_params = (domain, video_id, stream_num)
 122             f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
 123             m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
 124             for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
 125                 # URLs without the extra param induce an 404 error
 126                 entry.update({'extra_param_to_segment_url': hdcore_sign})
 127                 formats.append(entry)
 128             for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
 129                 mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
 130                 if mobj:
 131                     entry['format_id'] += mobj.group('tag')
 132                 formats.append(entry)
 133
 134             self._sort_formats(formats)
 135
 136         return {
 137             'id': video_id,
 138             'title': title,
 139             'formats': formats,
 140             'thumbnail': thumbnail,
 141         }