Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-31 00:32:52 +08:00
Code Issues Releases Wiki Activity

libsyn: adapt to new page structure and replace testcase

Browse Source
This commit is contained in:
Philipp Hagemeister 2018-03-20 23:07:11 +01:00
parent a66d1d079a
commit 3395958d2b
1 changed files with 35 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
youtube_dl/extractor/libsyn.py
View File

@ -1,24 +1,28 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import unified_strdate from ..utils import (
parse_duration,
unified_strdate,
)
class LibsynIE(InfoExtractor): class LibsynIE(InfoExtractor):
_VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))' _VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
_TESTS = [{ _TESTS = [{
'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/', 'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',
'md5': '443360ee1b58007bc3dcf09b41d093bb', 'md5': '2a55e75496c790cdeb058e7e6c087746',
'info_dict': { 'info_dict': {
'id': '3377616', 'id': '6385796',
'ext': 'mp3', 'ext': 'mp3',
'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart", 'title': "Champion Minded - Developing a Growth Mindset",
'description': 'md5:601cb790edd05908957dae8aaa866465', 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
'upload_date': '20150220', 'upload_date': '20180320',
'thumbnail': 're:^https?://.*', 'thumbnail': 're:^https?://.*',
}, },
}, { }, {
@ -39,31 +43,45 @@ class LibsynIE(InfoExtractor):
url = m.group('mainurl') url = m.group('mainurl')
webpage = self._download_webpage(url, video_id) 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( podcast_title = self._search_regex(
r'<h2>([^<]+)</h2>', webpage, 'podcast title', default=None) r'<h3>([^<]+)</h3>', webpage, 'podcast title', default=None)
if podcast_title:
podcast_title = podcast_title.strip()
episode_title = self._search_regex( episode_title = self._search_regex(
r'(?:<div class="episode-title">|<h3>)([^<]+)</', webpage, 'episode title') r'(?:<div class="episode-title">|<h4>)([^<]+)</', webpage, 'episode title')
if episode_title:
episode_title = episode_title.strip()
title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
description = self._html_search_regex( description = self._html_search_regex(
r'<div id="info_text_body">(.+?)</div>', webpage, r'<p\s+id="info_text_body">(.+?)</p>', webpage,
'description', default=None) 'description', default=None)
thumbnail = self._search_regex( if description:
r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"', # Strip non-breaking and normal spaces
webpage, 'thumbnail', fatal=False) description = description.replace('\u00A0', ' ').strip()
release_date = unified_strdate(self._search_regex( release_date = unified_strdate(self._search_regex(
r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False)) r'<div class="release_date">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 { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'upload_date': release_date, 'upload_date': release_date,
'duration': duration,
'formats': formats, 'formats': formats,
} }