from __future__ import unicode_literals
import re
+import itertools
from .common import InfoExtractor
from ..utils import (
+ clean_html,
+ dict_get,
ExtractorError,
float_or_none,
+ get_element_by_class,
int_or_none,
parse_duration,
parse_iso8601,
+ try_get,
unescapeHTML,
+ urlencode_postdata,
+ urljoin,
)
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
+ compat_urlparse,
)
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
- _ID_REGEX = r'[pb][\da-z]{7}'
+ _ID_REGEX = r'[pbw][\da-z]{7}'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?bbc\.co\.uk/
(?:
programmes/(?!articles/)|
iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
- music/clips[/#]|
- radio/player/
+ music/(?:clips|audiovideo/popular)[/#]|
+ radio/player/|
+ events/[^/]+/play/[^/]+/
)
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX
+ _LOGIN_URL = 'https://account.bbc.com/signin'
+ _NETRC_MACHINE = 'bbc'
+
_MEDIASELECTOR_URLS = [
# Provides HQ HLS streams with even better quality that pc mediaset but fails
# with geolocation in some cases when it's even not geo restricted at all (e.g.
}, {
'url': 'http://www.bbc.co.uk/radio/player/p03cchwf',
'only_matching': True,
- }
- ]
+ }, {
+ 'url': 'https://www.bbc.co.uk/music/audiovideo/popular#p055bc55',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.bbc.co.uk/programmes/w3csv1y9',
+ 'only_matching': True,
+ }]
+
+ _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
+
+ def _login(self):
+ username, password = self._get_login_info()
+ if username is None:
+ return
+
+ login_page = self._download_webpage(
+ self._LOGIN_URL, None, 'Downloading signin page')
+
+ login_form = self._hidden_inputs(login_page)
+
+ login_form.update({
+ 'username': username,
+ 'password': password,
+ })
+
+ post_url = urljoin(self._LOGIN_URL, self._search_regex(
+ r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
+ 'post url', default=self._LOGIN_URL, group='url'))
+
+ response, urlh = self._download_webpage_handle(
+ post_url, None, 'Logging in', data=urlencode_postdata(login_form),
+ headers={'Referer': self._LOGIN_URL})
+
+ if self._LOGIN_URL in urlh.geturl():
+ error = clean_html(get_element_by_class('form-message', response))
+ if error:
+ raise ExtractorError(
+ 'Unable to login: %s' % error, expected=True)
+ raise ExtractorError('Unable to log in')
+
+ def _real_initialize(self):
+ self._login()
class MediaSelectionError(Exception):
def __init__(self, id):
formats.extend(self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False))
+ if re.search(self._USP_RE, href):
+ usp_formats = self._extract_m3u8_formats(
+ re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href),
+ programme_id, ext='mp4', entry_protocol='m3u8_native',
+ m3u8_id=format_id, fatal=False)
+ for f in usp_formats:
+ if f.get('height') and f['height'] > 720:
+ continue
+ formats.append(f)
elif transfer_format == 'hds':
formats.extend(self._extract_f4m_formats(
href, programme_id, f4m_id=format_id, fatal=False))
else:
- if bitrate:
- format_id += '-%d' % bitrate
+ if not service and not supplier and bitrate:
+ format_id += '-%d' % bitrate
fmt = {
'format_id': format_id,
'filesize': file_size,
fmt.update({
'width': width,
'height': height,
- 'vbr': bitrate,
+ 'tbr': bitrate,
'vcodec': encoding,
})
else:
'acodec': encoding,
'vcodec': 'none',
})
- if protocol == 'http':
+ if protocol in ('http', 'https'):
# Direct link
fmt.update({
'url': href,
'rtmp_live': False,
'ext': 'flv',
})
+ else:
+ continue
formats.append(fmt)
elif kind == 'captions':
subtitles = self.extract_subtitles(media, programme_id)
description = smp_config['summary']
for item in smp_config['items']:
kind = item['kind']
- if kind != 'programme' and kind != 'radioProgramme':
+ if kind not in ('programme', 'radioProgramme'):
continue
programme_id = item.get('vpid')
duration = int_or_none(item.get('duration'))
for item in self._extract_items(playlist):
kind = item.get('kind')
- if kind != 'programme' and kind != 'radioProgramme':
+ if kind not in ('programme', 'radioProgramme'):
continue
title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
webpage = self._download_webpage(url, group_id, 'Downloading video page')
+ error = self._search_regex(
+ r'<div\b[^>]+\bclass=["\']smp__message delta["\'][^>]*>([^<]+)<',
+ webpage, 'error', default=None)
+ if error:
+ raise ExtractorError(error, expected=True)
+
programme_id = None
duration = None
# rtmp download
'skip_download': True,
}
+ }, {
+ # single video embedded with Morph
+ 'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
+ 'info_dict': {
+ 'id': 'p041vhd0',
+ 'ext': 'mp4',
+ 'title': "Nigeria v Japan - Men's First Round",
+ 'description': 'Live coverage of the first round from Group B at the Amazonia Arena.',
+ 'duration': 7980,
+ 'uploader': 'BBC Sport',
+ 'uploader_id': 'bbc_sport',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ 'skip': 'Georestricted to UK',
}, {
# single video with playlist.sxml URL in playlist param
'url': 'http://www.bbc.com/sport/0/football/33653409',
webpage = self._download_webpage(url, playlist_id)
- json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
+ json_ld_info = self._search_json_ld(webpage, playlist_id, default={})
timestamp = json_ld_info.get('timestamp')
playlist_title = json_ld_info.get('title')
'subtitles': subtitles,
}
+ # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
+ # There are several setPayload calls may be present but the video
+ # seems to be always related to the first one
+ morph_payload = self._parse_json(
+ self._search_regex(
+ r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
+ webpage, 'morph payload', default='{}'),
+ playlist_id, fatal=False)
+ if morph_payload:
+ components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
+ for component in components:
+ if not isinstance(component, dict):
+ continue
+ lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
+ if not lead_media:
+ continue
+ identifiers = lead_media.get('identifiers')
+ if not identifiers or not isinstance(identifiers, dict):
+ continue
+ programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
+ if not programme_id:
+ continue
+ title = lead_media.get('title') or self._og_search_title(webpage)
+ formats, subtitles = self._download_media_selector(programme_id)
+ self._sort_formats(formats)
+ description = lead_media.get('summary')
+ uploader = lead_media.get('masterBrand')
+ uploader_id = lead_media.get('mid')
+ duration = None
+ duration_d = lead_media.get('duration')
+ if isinstance(duration_d, dict):
+ duration = parse_duration(dict_get(
+ duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
+ return {
+ 'id': programme_id,
+ 'title': title,
+ 'description': description,
+ 'duration': duration,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ }
+
def extract_all(pattern):
return list(filter(None, map(
lambda s: self._parse_json(s, playlist_id, fatal=False),
r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
if entries:
return self.playlist_result(
- [self.url_result(entry, 'BBCCoUk') for entry in entries],
+ [self.url_result(entry_, 'BBCCoUk') for entry_ in entries],
playlist_id, playlist_title, playlist_description)
# Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
class BBCCoUkArticleIE(InfoExtractor):
- _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
IE_NAME = 'bbc.co.uk:article'
IE_DESC = 'BBC articles'
class BBCCoUkPlaylistBaseIE(InfoExtractor):
+ def _entries(self, webpage, url, playlist_id):
+ single_page = 'page' in compat_urlparse.parse_qs(
+ compat_urlparse.urlparse(url).query)
+ for page_num in itertools.count(2):
+ for video_id in re.findall(
+ self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
+ yield self.url_result(
+ self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
+ if single_page:
+ return
+ next_page = self._search_regex(
+ r'<li[^>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P<url>(?:(?!\2).)+)\2',
+ webpage, 'next page url', default=None, group='url')
+ if not next_page:
+ break
+ webpage = self._download_webpage(
+ compat_urlparse.urljoin(url, next_page), playlist_id,
+ 'Downloading page %d' % page_num, page_num)
+
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
- entries = [
- self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
- for video_id in re.findall(
- self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
-
title, description = self._extract_title_and_description(webpage)
- return self.playlist_result(entries, playlist_id, title, description)
+ return self.playlist_result(
+ self._entries(webpage, url, playlist_id),
+ playlist_id, title, description)
class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
'description': 'French thriller serial about a missing teenager.',
},
'playlist_mincount': 7,
+ }, {
+ # multipage playlist, explicit page
+ 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
+ 'info_dict': {
+ 'id': 'b00mfl7n',
+ 'title': 'Frozen Planet - Clips - BBC One',
+ 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
+ },
+ 'playlist_mincount': 24,
+ }, {
+ # multipage playlist, all pages
+ 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
+ 'info_dict': {
+ 'id': 'b00mfl7n',
+ 'title': 'Frozen Planet - Clips - BBC One',
+ 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
+ },
+ 'playlist_mincount': 142,
}, {
'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
'only_matching': True,
projects / youtube-dl / blobdiff