From a6ae61a4c28b28c10de5ff359bff81ce7b4547e8 Mon Sep 17 00:00:00 2001 From: nixxo Date: Sun, 28 Mar 2021 13:36:59 +0200 Subject: [PATCH] [la7] Add podcasts and podcast playlists (#198) Authored by: nixxo --- yt_dlp/extractor/extractors.py | 6 +- yt_dlp/extractor/la7.py | 144 +++++++++++++++++++++++++++++++++ 2 files changed, 149 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py index e8aa03a4f..482d526ab 100644 --- a/yt_dlp/extractor/extractors.py +++ b/yt_dlp/extractor/extractors.py @@ -582,7 +582,11 @@ from .kuwo import ( KuwoCategoryIE, KuwoMvIE, ) -from .la7 import LA7IE +from .la7 import ( + LA7IE, + LA7PodcastEpisodeIE, + LA7PodcastIE, +) from .laola1tv import ( Laola1TvEmbedIE, Laola1TvIE, diff --git a/yt_dlp/extractor/la7.py b/yt_dlp/extractor/la7.py index 74b006fb5..363fbd6a5 100644 --- a/yt_dlp/extractor/la7.py +++ b/yt_dlp/extractor/la7.py @@ -1,9 +1,15 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( + determine_ext, + float_or_none, + parse_duration, smuggle_url, + unified_strdate, ) @@ -57,3 +63,141 @@ class LA7IE(InfoExtractor): 'thumbnail': self._og_search_thumbnail(webpage, default=None), 'ie_key': 'Kaltura', } + + +class LA7PodcastEpisodeIE(InfoExtractor): + IE_NAME = 'la7.it:pod:episode' + _VALID_URL = r'''(?x)(https?://)? + (?:www\.)?la7\.it/[^/]+/podcast/([^/]+-)?(?P\d+)''' + + _TESTS = [{ + 'url': 'https://www.la7.it/voicetown/podcast/la-carezza-delle-memoria-di-carlo-verdone-23-03-2021-371497', + 'md5': '7737d4d79b3c1a34b3de3e16297119ed', + 'info_dict': { + 'id': '371497', + 'ext': 'mp3', + 'title': '"La carezza delle memoria" di Carlo Verdone', + 'description': 'md5:5abf07c3c551a687db80af3f9ceb7d52', + 'thumbnail': 'https://www.la7.it/sites/default/files/podcast/371497.jpg', + 'upload_date': '20210323', + }, + }, { + # embed url + 'url': 'https://www.la7.it/embed/podcast/371497', + 'only_matching': True, + }, { + # date already in the title + 'url': 'https://www.la7.it/propagandalive/podcast/lintervista-di-diego-bianchi-ad-annalisa-cuzzocrea-puntata-del-1932021-20-03-2021-371130', + 'only_matching': True, + }, { + # title same as show_title + 'url': 'https://www.la7.it/otto-e-mezzo/podcast/otto-e-mezzo-26-03-2021-372340', + 'only_matching': True, + }] + + def _extract_info(self, webpage, video_id=None, ppn=None): + if not video_id: + video_id = self._search_regex( + r'data-nid=([\'"])(?P\d+)\1', + webpage, 'video_id', group='vid') + + media_url = self._search_regex( + (r'src:\s*([\'"])(?P.+?mp3.+?)\1', + r'data-podcast=([\'"])(?P.+?mp3.+?)\1'), + webpage, 'media_url', group='url') + ext = determine_ext(media_url) + formats = [{ + 'url': media_url, + 'format_id': ext, + 'ext': ext, + }] + self._sort_formats(formats) + + title = self._html_search_regex( + (r'
(?P.+?)</', + r'<title>(?P<title>[^<]+)', + r'title:\s*([\'"])(?P.+?)\1'), + webpage, 'title', group='title') + + description = ( + self._html_search_regex( + (r'<div class="description">(.+?)</div>', + r'<div class="description-mobile">(.+?)</div>', + r'<div class="box-txt">([^<]+?)</div>', + r'<div class="field-content"><p>(.+?)</p></div>'), + webpage, 'description', default=None) + or self._html_search_meta('description', webpage)) + + thumb = self._html_search_regex( + (r'<div class="podcast-image"><img src="(.+?)"></div>', + r'<div class="container-embed"[^<]+url\((.+?)\);">', + r'<div class="field-content"><img src="(.+?)"'), + webpage, 'thumbnail', fatal=False, default=None) + + duration = parse_duration(self._html_search_regex( + r'<span class="(?:durata|duration)">([\d:]+)</span>', + webpage, 'duration', fatal=False, default=None)) + + date = self._html_search_regex( + r'class="data">\s*(?:<span>)?([\d\.]+)\s*</', + webpage, 'date', default=None) + + date_alt = self._search_regex( + r'(\d+[\./]\d+[\./]\d+)', title, 'date_alt', default=None) + ppn = ppn or self._search_regex( + r'ppN:\s*([\'"])(?P<ppn>.+?)\1', + webpage, 'ppn', group='ppn', default=None) + # if the date is not in the title + # and title is the same as the show_title + # add the date to the title + if date and not date_alt and ppn and ppn.lower() == title.lower(): + title += ' del %s' % date + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': float_or_none(duration), + 'formats': formats, + 'thumbnail': thumb, + 'upload_date': unified_strdate(date), + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + return self._extract_info(webpage, video_id) + + +class LA7PodcastIE(LA7PodcastEpisodeIE): + IE_NAME = 'la7.it:podcast' + _VALID_URL = r'(https?://)?(www\.)?la7\.it/(?P<id>[^/]+)/podcast/?(?:$|[#?])' + + _TESTS = [{ + 'url': 'https://www.la7.it/propagandalive/podcast', + 'info_dict': { + 'id': 'propagandalive', + 'title': "Propaganda Live", + }, + 'playlist_count': 10, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + + title = ( + self._html_search_regex( + r'<h1.*?>(.+?)</h1>', webpage, 'title', fatal=False, default=None) + or self._og_search_title(webpage)) + ppn = self._search_regex( + r'window\.ppN\s*=\s*([\'"])(?P<ppn>.+?)\1', + webpage, 'ppn', group='ppn', default=None) + + entries = [] + for episode in re.finditer( + r'<div class="container-podcast-property">([\s\S]+?)(?:</div>\s*){3}', + webpage): + entries.append(self._extract_info(episode.group(1), ppn=ppn)) + + return self.playlist_result(entries, playlist_id, title)