From 3395958d2befc710181bbde872074ce81eee9158 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 20 Mar 2018 23:07:11 +0100 Subject: [PATCH] libsyn: adapt to new page structure and replace testcase --- youtube_dl/extractor/libsyn.py | 52 +++++++++++++++++++++++----------- 1 file changed, 35 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/libsyn.py b/youtube_dl/extractor/libsyn.py index 4750b03a3f..f7311f4832 100644 --- a/youtube_dl/extractor/libsyn.py +++ b/youtube_dl/extractor/libsyn.py @@ -1,24 +1,28 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor -from ..utils import unified_strdate +from ..utils import ( + parse_duration, + unified_strdate, +) class LibsynIE(InfoExtractor): _VALID_URL = r'(?Phttps?://html5-player\.libsyn\.com/embed/episode/id/(?P[0-9]+))' _TESTS = [{ - 'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/', - 'md5': '443360ee1b58007bc3dcf09b41d093bb', + 'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/', + 'md5': '2a55e75496c790cdeb058e7e6c087746', 'info_dict': { - 'id': '3377616', + 'id': '6385796', 'ext': 'mp3', - 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart", - 'description': 'md5:601cb790edd05908957dae8aaa866465', - 'upload_date': '20150220', + 'title': "Champion Minded - Developing a Growth Mindset", + 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.', + 'upload_date': '20180320', 'thumbnail': 're:^https?://.*', }, }, { @@ -39,31 +43,45 @@ class LibsynIE(InfoExtractor): url = m.group('mainurl') webpage = self._download_webpage(url, video_id) - formats = [{ - 'url': media_url, - } for media_url in set(re.findall(r'var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))] - podcast_title = self._search_regex( - r'

([^<]+)

', webpage, 'podcast title', default=None) + r'

([^<]+)

', webpage, 'podcast title', default=None) + if podcast_title: + podcast_title = podcast_title.strip() episode_title = self._search_regex( - r'(?:
|

)([^<]+)|

)([^<]+)(.+?)

', webpage, + r'(.+?)

', webpage, 'description', default=None) - thumbnail = self._search_regex( - r']+class="info-show-icon"[^>]+src="([^"]+)"', - webpage, 'thumbnail', fatal=False) + if description: + # Strip non-breaking and normal spaces + description = description.replace('\u00A0', ' ').strip() release_date = unified_strdate(self._search_regex( r'
Released: ([^<]+)<', webpage, 'release date', fatal=False)) + data_json = self._search_regex(r'var\s+playlistItem\s*=\s*(\{.*?\});\n', webpage, 'JSON data block') + data = json.loads(data_json) + + formats = [{ + 'url': data['media_url'], + 'format_id': 'main', + }, { + 'url': data['media_url_libsyn'], + 'format_id': 'libsyn', + }] + thumbnail = data.get('thumbnail_url') + duration = parse_duration(data.get('duration')) + return { 'id': video_id, 'title': title, 'description': description, 'thumbnail': thumbnail, 'upload_date': release_date, + 'duration': duration, 'formats': formats, }