]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/cspan.py
3 from .common
import InfoExtractor
4 from ..compat
import compat_HTMLParseError
10 get_element_by_attribute
,
22 from .senategov
import SenateISVPIE
23 from .ustream
import UstreamIE
26 class CSpanIE(InfoExtractor
):
27 _VALID_URL
= r
'https?://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
30 'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
31 'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
34 'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
36 'playlist_mincount': 2,
37 'skip': 'Regularly fails on travis, for unknown reasons',
39 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
44 'title': 'CSPAN - International Health Care Models',
45 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
48 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
51 'title': 'General Motors Ignition Switch Recall',
53 'playlist_mincount': 6,
55 # Video from senate.gov
56 'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
58 'id': 'judiciary031715',
60 'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
63 'skip_download': True, # m3u8 downloads
66 # Ustream embedded video
67 'url': 'https://www.c-span.org/video/?114917-1/armed-services',
71 'title': 'USHR07 Armed Services Committee',
72 'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee',
73 'timestamp': 1423060374,
74 'upload_date': '20150204',
75 'uploader': 'HouseCommittee',
76 'uploader_id': '12987475',
80 'url': 'https://www.c-span.org/video/?437336-1/judiciary-antitrust-competition-policy-consumer-rights',
81 'only_matching': True,
83 BRIGHTCOVE_URL_TEMPLATE
= 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
85 def _real_extract(self
, url
):
86 video_id
= self
._match
_id
(url
)
88 webpage
= self
._download
_webpage
(url
, video_id
)
90 ustream_url
= UstreamIE
._extract
_url
(webpage
)
92 return self
.url_result(ustream_url
, UstreamIE
.ie_key())
95 bc
= self
._search
_regex
(
96 r
"(<[^>]+id='brightcove-player-embed'[^>]+>)",
97 webpage
, 'brightcove embed', default
=None)
99 bc_attr
= extract_attributes(bc
)
100 bc_url
= self
.BRIGHTCOVE_URL_TEMPLATE
% (
101 bc_attr
.get('data-bcaccountid', '3162030207001'),
102 bc_attr
.get('data-noprebcplayerid', 'SyGGpuJy3g'),
103 bc_attr
.get('data-newbcplayerid', 'default'),
104 bc_attr
['data-bcid'])
105 return self
.url_result(smuggle_url(bc_url
, {'source_url': url}
))
107 def add_referer(formats
):
109 f
.setdefault('http_headers', {})['Referer'] = url
111 # As of 01.12.2020 this path looks to cover all cases making the rest
112 # of the code unnecessary
113 jwsetup
= self
._parse
_json
(
115 r
'(?s)jwsetup\s*=\s*({.+?})\s*;', webpage
, 'jwsetup',
117 video_id
, transform_source
=js_to_json
, fatal
=False)
119 info
= self
._parse
_jwplayer
_data
(
120 jwsetup
, video_id
, require_title
=False, m3u8_id
='hls',
122 add_referer(info
['formats'])
123 for subtitles
in info
['subtitles'].values():
124 for subtitle
in subtitles
:
125 ext
= determine_ext(subtitle
['url'])
128 subtitle
['ext'] = ext
129 ld_info
= self
._search
_json
_ld
(webpage
, video_id
, default
={})
131 title
= get_element_by_class('video-page-title', webpage
)
132 except compat_HTMLParseError
:
135 title
= self
._og
_search
_title
(webpage
)
136 description
= get_element_by_attribute('itemprop', 'description', webpage
) or \
137 self
._html
_search
_meta
(['og:description', 'description'], webpage
)
138 return merge_dicts(info
, ld_info
, {
140 'thumbnail': get_element_by_attribute('itemprop', 'thumbnailUrl', webpage
),
141 'description': description
,
142 'timestamp': parse_iso8601(get_element_by_attribute('itemprop', 'uploadDate', webpage
)),
143 'location': get_element_by_attribute('itemprop', 'contentLocation', webpage
),
144 'duration': int_or_none(self
._search
_regex
(
145 r
'jwsetup\.seclength\s*=\s*(\d+);',
146 webpage
, 'duration', fatal
=False)),
147 'view_count': str_to_int(self
._search
_regex
(
148 r
"<span[^>]+class='views'[^>]*>([\d,]+)\s+Views</span>",
149 webpage
, 'views', fatal
=False)),
153 # We first look for clipid, because clipprog always appears before
154 patterns
= [r
'id=\'clip(%s)\'\s
*value
=\'([0-9]+)\'' % t for t in ('id', 'prog
')]
155 results = list(filter(None, (re.search(p, webpage) for p in patterns)))
158 video_type, video_id = matches.groups()
159 video_type = 'clip
' if video_type == 'id' else 'program
'
161 m = re.search(r'data
-(?P
<type>clip|prog
)id=["\'](?P<id>\d+)', webpage)
163 video_id = m.group('id')
164 video_type = 'program' if m.group('type') == 'prog' else 'clip'
166 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
168 title = self._og_search_title(webpage)
169 surl = smuggle_url(senate_isvp_url, {'force_title': title})
170 return self.url_result(surl, 'SenateISVP', video_id, title)
171 video_id = self._search_regex(
172 r'jwsetup\.clipprog\s*=\s*(\d+);',
173 webpage, 'jwsetup program id', default=None)
175 video_type = 'program'
176 if video_type is None or video_id is None:
177 error_message = get_element_by_class('VLplayer-error-message', webpage)
179 raise ExtractorError(error_message)
180 raise ExtractorError('unable to find video id and type')
182 def get_text_attr(d, attr):
183 return d.get(attr, {}).get('#text')
185 data = self._download_json(
186 'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
188 if data['@status'] != 'Success':
189 raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
191 doc = self._download_xml(
192 'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
195 description = self._html_search_meta('description', webpage)
197 title = find_xpath_attr(doc, './/string', 'name', 'title').text
198 thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
200 files = data['files']
201 capfile = get_text_attr(data, 'capfile')
204 for partnum, f in enumerate(files):
206 for quality in f.get('qualities', []):
208 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
209 'url': unescapeHTML(get_text_attr(quality, 'file')),
210 'height': int_or_none(get_text_attr(quality, 'height')),
211 'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
214 path = unescapeHTML(get_text_attr(f, 'path'))
217 formats = self._extract_m3u8_formats(
218 path, video_id, 'mp4', entry_protocol='m3u8_native',
219 m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
221 self._sort_formats(formats)
223 'id': '%s_%d' % (video_id, partnum + 1),
225 title if len(files) == 1 else
226 '%s part %d' % (title, partnum + 1)),
228 'description': description,
229 'thumbnail': thumbnail,
230 'duration': int_or_none(get_text_attr(f, 'length')),
234 'ext': determine_ext(capfile, 'dfxp')
236 } if capfile else None,
239 if len(entries) == 1:
240 entry = dict(entries[0])
241 entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
248 'id': 'c' + video_id if video_type == 'clip' else video_id,
252 class CSpanCongressIE(InfoExtractor):
253 _VALID_URL = r'https?://(?:www\.)?c-span\.org/congress/'
255 'url': 'https://www.c-span.org/congress/?chamber=house&date=2017-12-13&t=1513208380',
257 'id': 'house_2017-12-13',
258 'title': 'Congressional Chronicle - Members of Congress, Hearings and More',
259 'description': 'md5:54c264b7a8f219937987610243305a84',
260 'thumbnail': r're:https://ximage.c-spanvideo.org/.+',
265 def _real_extract(self, url):
266 query = parse_qs(url)
267 video_date = query.get('date', [None])[0]
268 video_id = join_nonempty(query.get('chamber', ['senate'])[0], video_date, delim='_')
269 webpage = self._download_webpage(url, video_id)
271 jwp_date = re.search(r'jwsetup.clipprogdate = \'(?P<date>\d{4}-\d{2}-\d{2})\';', webpage)
273 video_id = f'{video_id}_{jwp_date.group("date")}'
274 jwplayer_data = self._parse_json(
275 self._search_regex(r'jwsetup\s*=\s*({(?:.|\n)[^;]+});', webpage, 'player config'),
276 video_id, transform_source=js_to_json)
278 title = (self._og_search_title(webpage, default=None)
279 or self._html_extract_title(webpage, 'video title'))
280 description = (self._og_search_description(webpage, default=None)
281 or self._html_search_meta('description', webpage, 'description', default=None))
284 **self._parse_jwplayer_data(jwplayer_data, video_id, False),
285 'title': re.sub(r'\s+', ' ', title.split('|')[0]).strip(),
286 'description': description,
287 'http_headers': {'Referer': 'https://www.c-span.org/'},