depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-22 00:37:41 +00:00
Code Issues Releases Wiki Activity

[bbc:playlist] Add support for pagination (Closes #10349)

Browse source
This commit is contained in:
Sergey M․ 2016-08-16 04:36:23 +07:00
parent 818ac213eb
commit 254e64a20a
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 42 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

48
youtube_dl/extractor/bbc.py
View file

@ -2,6 +2,7 @@
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..utils import (
@ -17,6 +18,7 @@ from ..utils import (
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
compat_urlparse,
)
@ -1056,19 +1058,35 @@ class BBCCoUkArticleIE(InfoExtractor):
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):
@ -1094,6 +1112,24 @@ class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
},
'playlist_mincount': 10,
}, {
# explicit page
'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
'info_dict': {
'id': 'b00mfl7n',
'title': 'Bohemian Icons',
'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
},
'playlist_mincount': 24,
}, {
# all pages
'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
'info_dict': {
'id': 'b00mfl7n',
'title': 'Bohemian Icons',
'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
},
'playlist_mincount': 142,
}]
def _extract_title_and_description(self, webpage):