yt-dlp/yt_dlp/extractor/cspan.py

291 lines
12 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-26 17:55:54 +02:00
import re
from .common import InfoExtractor
from ..compat import compat_HTMLParseError
2013-06-26 17:55:54 +02:00
from ..utils import (
2015-04-24 17:46:51 +02:00
determine_ext,
ExtractorError,
extract_attributes,
find_xpath_attr,
2021-01-16 13:40:15 +01:00
get_element_by_attribute,
get_element_by_class,
int_or_none,
join_nonempty,
2021-01-01 13:26:37 +01:00
js_to_json,
merge_dicts,
2021-01-16 13:40:15 +01:00
parse_iso8601,
parse_qs,
smuggle_url,
2021-01-16 13:40:15 +01:00
str_to_int,
unescapeHTML,
2013-06-26 17:55:54 +02:00
)
from .senategov import SenateISVPIE
from .ustream import UstreamIE
2013-06-26 17:55:54 +02:00
2013-06-26 17:55:54 +02:00
class CSpanIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
IE_DESC = 'C-SPAN'
_TESTS = [{
'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
'info_dict': {
'id': '315139',
'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
2013-06-27 20:46:46 +02:00
},
2017-01-20 15:25:20 +01:00
'playlist_mincount': 2,
'skip': 'Regularly fails on travis, for unknown reasons',
}, {
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
2017-01-20 15:25:20 +01:00
# md5 is unstable
'info_dict': {
'id': 'c4486943',
'ext': 'mp4',
'title': 'CSPAN - International Health Care Models',
'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
}
}, {
'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
'info_dict': {
'id': '342759',
'title': 'General Motors Ignition Switch Recall',
},
2017-01-20 15:25:20 +01:00
'playlist_mincount': 6,
}, {
# Video from senate.gov
'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
'info_dict': {
'id': 'judiciary031715',
'ext': 'mp4',
'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
},
'params': {
'skip_download': True, # m3u8 downloads
}
}, {
# Ustream embedded video
'url': 'https://www.c-span.org/video/?114917-1/armed-services',
'info_dict': {
'id': '58428542',
'ext': 'flv',
'title': 'USHR07 Armed Services Committee',
'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee',
'timestamp': 1423060374,
'upload_date': '20150204',
'uploader': 'HouseCommittee',
'uploader_id': '12987475',
},
}, {
# Audio Only
'url': 'https://www.c-span.org/video/?437336-1/judiciary-antitrust-competition-policy-consumer-rights',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
2013-06-26 17:55:54 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
video_type = None
webpage = self._download_webpage(url, video_id)
ustream_url = UstreamIE._extract_url(webpage)
if ustream_url:
return self.url_result(ustream_url, UstreamIE.ie_key())
if '&vod' not in url:
bc = self._search_regex(
r"(<[^>]+id='brightcove-player-embed'[^>]+>)",
webpage, 'brightcove embed', default=None)
if bc:
bc_attr = extract_attributes(bc)
bc_url = self.BRIGHTCOVE_URL_TEMPLATE % (
bc_attr.get('data-bcaccountid', '3162030207001'),
bc_attr.get('data-noprebcplayerid', 'SyGGpuJy3g'),
bc_attr.get('data-newbcplayerid', 'default'),
bc_attr['data-bcid'])
return self.url_result(smuggle_url(bc_url, {'source_url': url}))
2021-01-01 13:26:37 +01:00
def add_referer(formats):
for f in formats:
f.setdefault('http_headers', {})['Referer'] = url
# As of 01.12.2020 this path looks to cover all cases making the rest
# of the code unnecessary
jwsetup = self._parse_json(
self._search_regex(
r'(?s)jwsetup\s*=\s*({.+?})\s*;', webpage, 'jwsetup',
default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if jwsetup:
info = self._parse_jwplayer_data(
jwsetup, video_id, require_title=False, m3u8_id='hls',
base_url=url)
add_referer(info['formats'])
2021-01-16 13:40:15 +01:00
for subtitles in info['subtitles'].values():
for subtitle in subtitles:
ext = determine_ext(subtitle['url'])
if ext == 'php':
ext = 'vtt'
subtitle['ext'] = ext
2021-01-01 13:26:37 +01:00
ld_info = self._search_json_ld(webpage, video_id, default={})
try:
title = get_element_by_class('video-page-title', webpage)
except compat_HTMLParseError:
title = None
if title is None:
title = self._og_search_title(webpage)
2021-01-16 13:40:15 +01:00
description = get_element_by_attribute('itemprop', 'description', webpage) or \
self._html_search_meta(['og:description', 'description'], webpage)
return merge_dicts(info, ld_info, {
'title': title,
'thumbnail': get_element_by_attribute('itemprop', 'thumbnailUrl', webpage),
'description': description,
'timestamp': parse_iso8601(get_element_by_attribute('itemprop', 'uploadDate', webpage)),
'location': get_element_by_attribute('itemprop', 'contentLocation', webpage),
'duration': int_or_none(self._search_regex(
r'jwsetup\.seclength\s*=\s*(\d+);',
webpage, 'duration', fatal=False)),
'view_count': str_to_int(self._search_regex(
r"<span[^>]+class='views'[^>]*>([\d,]+)\s+Views</span>",
webpage, 'views', fatal=False)),
})
2021-01-01 13:26:37 +01:00
# Obsolete
2015-12-28 13:48:10 +01:00
# We first look for clipid, because clipprog always appears before
patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
results = list(filter(None, (re.search(p, webpage) for p in patterns)))
if results:
matches = results[0]
video_type, video_id = matches.groups()
2015-12-28 13:48:10 +01:00
video_type = 'clip' if video_type == 'id' else 'program'
else:
m = re.search(r'data-(?P<type>clip|prog)id=["\'](?P<id>\d+)', webpage)
if m:
video_id = m.group('id')
video_type = 'program' if m.group('type') == 'prog' else 'clip'
else:
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
title = self._og_search_title(webpage)
surl = smuggle_url(senate_isvp_url, {'force_title': title})
return self.url_result(surl, 'SenateISVP', video_id, title)
video_id = self._search_regex(
r'jwsetup\.clipprog\s*=\s*(\d+);',
webpage, 'jwsetup program id', default=None)
if video_id:
video_type = 'program'
if video_type is None or video_id is None:
error_message = get_element_by_class('VLplayer-error-message', webpage)
if error_message:
raise ExtractorError(error_message)
raise ExtractorError('unable to find video id and type')
2015-11-28 20:22:31 +01:00
def get_text_attr(d, attr):
return d.get(attr, {}).get('#text')
data = self._download_json(
'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
video_id)['video']
if data['@status'] != 'Success':
2015-11-28 20:22:31 +01:00
raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
doc = self._download_xml(
'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
video_id)
description = self._html_search_meta('description', webpage)
title = find_xpath_attr(doc, './/string', 'name', 'title').text
thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
files = data['files']
2015-11-28 20:22:31 +01:00
capfile = get_text_attr(data, 'capfile')
entries = []
for partnum, f in enumerate(files):
formats = []
for quality in f.get('qualities', []):
formats.append({
2015-11-28 20:22:31 +01:00
'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
'url': unescapeHTML(get_text_attr(quality, 'file')),
'height': int_or_none(get_text_attr(quality, 'height')),
'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
})
if not formats:
2016-01-29 19:26:33 +01:00
path = unescapeHTML(get_text_attr(f, 'path'))
if not path:
continue
formats = self._extract_m3u8_formats(
path, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
2021-01-01 13:26:37 +01:00
add_referer(formats)
self._sort_formats(formats)
entries.append({
'id': '%s_%d' % (video_id, partnum + 1),
'title': (
title if len(files) == 1 else
'%s part %d' % (title, partnum + 1)),
'formats': formats,
'description': description,
'thumbnail': thumbnail,
2015-11-28 20:22:31 +01:00
'duration': int_or_none(get_text_attr(f, 'length')),
'subtitles': {
'en': [{
'url': capfile,
'ext': determine_ext(capfile, 'dfxp')
}],
} if capfile else None,
})
if len(entries) == 1:
entry = dict(entries[0])
entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
return entry
else:
return {
'_type': 'playlist',
'entries': entries,
'title': title,
'id': 'c' + video_id if video_type == 'clip' else video_id,
}
class CSpanCongressIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?c-span\.org/congress/'
_TESTS = [{
'url': 'https://www.c-span.org/congress/?chamber=house&date=2017-12-13&t=1513208380',
'info_dict': {
'id': 'house_2017-12-13',
'title': 'Congressional Chronicle - Members of Congress, Hearings and More',
'description': 'md5:54c264b7a8f219937987610243305a84',
'thumbnail': r're:https://ximage.c-spanvideo.org/.+',
'ext': 'mp4'
}
}]
def _real_extract(self, url):
query = parse_qs(url)
video_date = query.get('date', [None])[0]
video_id = join_nonempty(query.get('chamber', ['senate'])[0], video_date, delim='_')
webpage = self._download_webpage(url, video_id)
if not video_date:
jwp_date = re.search(r'jwsetup.clipprogdate = \'(?P<date>\d{4}-\d{2}-\d{2})\';', webpage)
if jwp_date:
video_id = f'{video_id}_{jwp_date.group("date")}'
jwplayer_data = self._parse_json(
self._search_regex(r'jwsetup\s*=\s*({(?:.|\n)[^;]+});', webpage, 'player config'),
video_id, transform_source=js_to_json)
title = (self._og_search_title(webpage, default=None)
or self._html_search_regex(r'(?s)<title>(.*?)</title>', webpage, 'video title'))
description = (self._og_search_description(webpage, default=None)
or self._html_search_meta('description', webpage, 'description', default=None))
return {
**self._parse_jwplayer_data(jwplayer_data, video_id, False),
'title': re.sub(r'\s+', ' ', title.split('|')[0]).strip(),
'description': description,
'http_headers': {'Referer': 'https://www.c-span.org/'},
}