From 254e64a20aa37a033cb200bc6f1aa9daf57eead8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 16 Aug 2016 04:36:23 +0700 Subject: [PATCH] [bbc:playlist] Add support for pagination (Closes #10349) --- youtube_dl/extractor/bbc.py | 48 ++++++++++++++++++++++++++++++++----- 1 file changed, 42 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 83e6d024c..16a97a76d 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -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 ..compat import ( compat_etree_fromstring, compat_HTTPError, + compat_urlparse, ) @@ -1056,19 +1058,35 @@ def _real_extract(self, url): 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']+class=(["\'])pagination_+next\1[^>]*>]+href=(["\'])(?P(?:(?!\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):