-import xml.etree.ElementTree
import functools
import itertools
import json
import re
+import urllib.error
+import xml.etree.ElementTree
from .common import InfoExtractor
-from ..compat import (
- compat_HTTPError,
- compat_str,
- compat_urllib_error,
- compat_urlparse,
-)
+from ..compat import compat_HTTPError, compat_str, compat_urlparse
from ..utils import (
ExtractorError,
OnDemandPagedList,
)
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX
+ _EMBED_REGEX = [r'setPlaylist\("(?P<url>https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)']
_LOGIN_URL = 'https://account.bbc.com/signin'
_NETRC_MACHINE = 'bbc'
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
except ExtractorError as e:
- if not (isinstance(e.exc_info[1], compat_urllib_error.HTTPError)
+ if not (isinstance(e.exc_info[1], urllib.error.HTTPError)
and e.exc_info[1].code in (403, 404)):
raise
fmts = []
else:
programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
- self._sort_formats(formats)
-
return {
'id': programme_id,
'title': title,
}
-class BBCIE(BBCCoUkIE):
+class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'bbc'
IE_DESC = 'BBC'
- _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
+ _VALID_URL = r'''(?x)
+ https?://(?:www\.)?(?:
+ bbc\.(?:com|co\.uk)|
+ bbcnewsd73hkzno2ini43t4gblxvycyac5aw4gnv7t2rccijh7745uqd\.onion|
+ bbcweb3hytmzhn5d532owbu6oqadra5z3ar726vq5kgwwn6aucdccrad\.onion
+ )/(?:[^/]+/)+(?P<id>[^/#?]+)'''
_MEDIA_SETS = [
'pc',
'upload_date': '20190604',
'categories': ['Psychology'],
},
+ }, { # onion routes
+ 'url': 'https://www.bbcnewsd73hkzno2ini43t4gblxvycyac5aw4gnv7t2rccijh7745uqd.onion/news/av/world-europe-63208576',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.bbcweb3hytmzhn5d532owbu6oqadra5z3ar726vq5kgwwn6aucdccrad.onion/sport/av/football/63195681',
+ 'only_matching': True,
}]
@classmethod
def _extract_from_playlist_sxml(self, url, playlist_id, timestamp):
programme_id, title, description, duration, formats, subtitles = \
self._process_legacy_playlist_url(url, playlist_id)
- self._sort_formats(formats)
return {
'id': programme_id,
'title': title,
json_ld_info = self._search_json_ld(webpage, playlist_id, default={})
timestamp = json_ld_info.get('timestamp')
- playlist_title = json_ld_info.get('title')
- if not playlist_title:
- playlist_title = (self._og_search_title(webpage, default=None)
- or self._html_extract_title(webpage, 'playlist title', default=None))
- if playlist_title:
- playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
+ playlist_title = json_ld_info.get('title') or re.sub(
+ r'(.+)\s*-\s*BBC.*?$', r'\1', self._generic_title('', webpage, default='')).strip() or None
playlist_description = json_ld_info.get(
'description') or self._og_search_description(webpage, default=None)
duration = int_or_none(items[0].get('duration'))
programme_id = items[0].get('vpid')
formats, subtitles = self._download_media_selector(programme_id)
- self._sort_formats(formats)
entries.append({
'id': programme_id,
'title': title,
continue
raise
if entry:
- self._sort_formats(entry['formats'])
entries.append(entry)
if entries:
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
- self._sort_formats(formats)
# digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
digital_data = self._parse_json(
self._search_regex(
if version_id:
title = smp_data['title']
formats, subtitles = self._download_media_selector(version_id)
- self._sort_formats(formats)
image_url = smp_data.get('holdingImageURL')
display_date = init_data.get('displayDate')
topic_title = init_data.get('topicTitle')
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')
if current_programme and programme_id and current_programme.get('type') == 'playable_item':
title = current_programme.get('titles', {}).get('tertiary') or playlist_title
formats, subtitles = self._download_media_selector(programme_id)
- self._sort_formats(formats)
synopses = current_programme.get('synopses') or {}
network = current_programme.get('network') or {}
duration = int_or_none(
clip_title = clip.get('title')
if clip_vpid and clip_title:
formats, subtitles = self._download_media_selector(clip_vpid)
- self._sort_formats(formats)
return {
'id': clip_vpid,
'title': clip_title,
if not programme_id:
continue
formats, subtitles = self._download_media_selector(programme_id)
- self._sort_formats(formats)
entries.append({
'id': programme_id,
'title': playlist_title,
if not (item_id and item_title):
continue
formats, subtitles = self._download_media_selector(item_id)
- self._sort_formats(formats)
item_desc = None
blocks = try_get(media, lambda x: x['summary']['blocks'], list)
if blocks:
(lambda x: x['data']['blocks'],
lambda x: x['data']['content']['model']['blocks'],),
list) or []):
- if block.get('type') != 'media':
+ if block.get('type') not in ['media', 'video']:
continue
parse_media(block.get('model'))
return self.playlist_result(
formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
if not formats and not self.get_param('ignore_no_formats'):
continue
- self._sort_formats(formats)
video_id = media_meta.get('externalId')
if not video_id: