From 8d3737cda7bb710c6de96c26602d48f75ef95537 Mon Sep 17 00:00:00 2001 From: Jakub Adam Wieczorek Date: Thu, 25 Aug 2016 23:04:59 +0200 Subject: [PATCH] [polskieradio] Add support for downloading whole programmes. This extends the Polskie Radio (the Polish national radio) extractor to enable the user to download all the broadcasts of a single programme. --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/polskieradio.py | 79 ++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f72faa8a7..f8f91f13d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -667,7 +667,7 @@ from .pluralsight import ( ) from .podomatic import PodomaticIE from .pokemon import PokemonIE -from .polskieradio import PolskieRadioIE +from .polskieradio import PolskieRadioIE, PolskieRadioProgrammeIE from .porn91 import Porn91IE from .porncom import PornComIE from .pornhd import PornHdIE diff --git a/youtube_dl/extractor/polskieradio.py b/youtube_dl/extractor/polskieradio.py index f559b899f..c51d3d9be 100644 --- a/youtube_dl/extractor/polskieradio.py +++ b/youtube_dl/extractor/polskieradio.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse_unquote, + compat_urlparse ) from ..utils import ( int_or_none, @@ -15,6 +16,84 @@ from ..utils import ( ) +class PolskieRadioProgrammeIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+(,[^/]+)?/(?P\d+)' + _TESTS = [{ + 'url': 'http://www.polskieradio.pl/7/5102,HISTORIA-ZYWA', + 'info_dict': { + 'id': '5102', + 'title': 'HISTORIA ŻYWA', + }, + 'playlist_mincount': 34, + }, { + 'url': 'http://www.polskieradio.pl/7/4807', + 'info_dict': { + 'id': '4807', + 'title': 'Vademecum 1050. rocznicy Chrztu Polski' + }, + 'playlist_mincount': 5 + }, { + 'url': 'http://www.polskieradio.pl/7/129,Sygnaly-dnia?ref=source', + 'only_matching': True + }, { + 'url': 'http://www.polskieradio.pl/37,RedakcjaKatolicka/4143,Kierunek-Krakow', + 'info_dict': { + 'id': '4143', + 'title': 'Kierunek Kraków', + }, + 'playlist_mincount': 61 + }, { + 'url': 'http://www.polskieradio.pl/7,Jedynka/5102,HISTORIA-ZYWA', + 'only_matching': True + }] + + def _get_entries_from_page_content(self, base_url, content): + entries = [] + + articles = re.findall( + r'
\s+', + content) + for article_id, article_url, _, article_title in articles: + resolved_article_url = compat_urlparse.urljoin(base_url, article_url) + entries.append(self.url_result( + resolved_article_url, + ie='PolskieRadio', + video_id=article_id, + video_title=article_title)) + + return entries + + @classmethod + def suitable(cls, url): + return False if PolskieRadioIE.suitable(url) else super(PolskieRadioProgrammeIE, cls).suitable(url) + + def _real_extract(self, url): + programme_id = self._match_id(url) + webpage = self._download_webpage(url, programme_id) + + title = self._html_search_regex( + r'(.+?)', + webpage, 'title', fatal=False) + description = None + + entries = self._get_entries_from_page_content(url, webpage) + + pages = re.findall(r' 1: + page_url_root = next(url for _, url, _ in pages if len(url) > 0) + for page_number in range(2, page_count + 1): + page_url = page_url_root + str(page_number) + resolved_page_url = compat_urlparse.urljoin(url, page_url) + page_content = self._download_webpage( + resolved_page_url, programme_id, + note="Downloading page number %d" % page_number) + entries.extend(self._get_entries_from_page_content(url, page_content)) + + return self.playlist_result(entries, programme_id, title, description) + + class PolskieRadioIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+/\d+/Artykul/(?P[0-9]+)' _TESTS = [{