aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/bbc.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/bbc.py')
-rw-r--r--youtube_dl/extractor/bbc.py61
1 files changed, 48 insertions, 13 deletions
diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index 68995f81e..7fb80aa38 100644
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -2,7 +2,6 @@
from __future__ import unicode_literals
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
@@ -14,18 +13,22 @@ from ..utils import (
remove_end,
unescapeHTML,
)
-from ..compat import compat_HTTPError
+from ..compat import (
+ compat_etree_fromstring,
+ compat_HTTPError,
+)
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
- _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
+ _ID_REGEX = r'[pb][\da-z]{7}'
+ _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>%s)' % _ID_REGEX
_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.
- # http://www.bbc.co.uk/programmes/b06bp7lf)
+ # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable.
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
]
@@ -332,7 +335,7 @@ class BBCCoUkIE(InfoExtractor):
return self._download_media_selector_url(
mediaselector_url % programme_id, programme_id)
except BBCCoUkIE.MediaSelectionError as e:
- if e.id in ('notukerror', 'geolocation'):
+ if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
last_exception = e
continue
self._raise_extractor_error(e)
@@ -343,8 +346,8 @@ class BBCCoUkIE(InfoExtractor):
media_selection = self._download_xml(
url, programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
- if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
- media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
+ if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
+ media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
else:
raise
return self._process_media_selector(media_selection, programme_id)
@@ -421,7 +424,7 @@ class BBCCoUkIE(InfoExtractor):
continue
title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
- description = description_el.text if description_el else None
+ description = description_el.text if description_el is not None else None
def get_programme_id(item):
def get_from_attributes(item):
@@ -463,7 +466,7 @@ class BBCCoUkIE(InfoExtractor):
if not programme_id:
programme_id = self._search_regex(
- r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+ r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
@@ -625,6 +628,7 @@ class BBCIE(BBCCoUkIE):
'id': 'p02xycnp',
'ext': 'mp4',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
+ 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
'duration': 140,
},
'params': {
@@ -651,7 +655,7 @@ class BBCIE(BBCCoUkIE):
@classmethod
def suitable(cls, url):
- return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url)
+ return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
def _extract_from_media_meta(self, media_meta, video_id):
# Direct links to media in media metadata (e.g.
@@ -777,8 +781,9 @@ class BBCIE(BBCCoUkIE):
# single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
programme_id = self._search_regex(
- [r'data-video-player-vpid="([\da-z]{8})"',
- r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
+ [r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
+ r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
+ r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
webpage, 'vpid', default=None)
if programme_id:
@@ -813,7 +818,7 @@ class BBCIE(BBCCoUkIE):
# Multiple video article (e.g.
# http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
- EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+ EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
entries = []
for match in extract_all(r'new\s+SMP\(({.+?})\)'):
embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
@@ -902,3 +907,33 @@ class BBCIE(BBCCoUkIE):
})
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
+
+
+class BBCCoUkArticleIE(InfoExtractor):
+ _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+ IE_NAME = 'bbc.co.uk:article'
+ IE_DESC = 'BBC articles'
+
+ _TEST = {
+ 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
+ 'info_dict': {
+ 'id': '3jNQLTMrPlYGTBn0WV6M2MS',
+ 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
+ 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
+ },
+ 'playlist_count': 4,
+ 'add_ie': ['BBCCoUk'],
+ }
+
+ def _real_extract(self, url):
+ playlist_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage).strip()
+
+ entries = [self.url_result(programme_url) for programme_url in re.findall(
+ r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
+
+ return self.playlist_result(entries, playlist_id, title, description)