R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[cjsw] Requested fixes

Browse Source
This commit is contained in:
Christopher Smith 2017-07-04 15:36:48 -06:00
parent 969c0fe31c
commit dbae412d05
1 changed files with 8 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/cjsw.py
View File

@ -1,17 +1,14 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
unescapeHTML,
) )
class CJSWIE(InfoExtractor): class CJSWIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program_name>[\S]+)/(?P<id>[0-9]+)/?' _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/\S+/(?P<id>[0-9]+)'
IE_NAME = 'cjsw' IE_NAME = 'cjsw'
_TEST = { _TEST = {
'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620', 'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
@ -29,18 +26,19 @@ class CJSWIE(InfoExtractor):
webpage = self._download_webpage(url, episode_id) webpage = self._download_webpage(url, episode_id)
episode_controls = re.search(r'<div[^>]+class=(["\'])episode-controls\1[^>]*>', webpage) episode_controls = self._search_regex(r'<div[^>]+class=(["\'])episode-controls\1[^>]*>', webpage, 'episode_controls', fatal=False)
if not episode_controls: if not episode_controls:
raise ExtractorError('No streamable podcast', video_id=episode_id, expected=True) raise ExtractorError('No streamable podcast', video_id=episode_id, expected=True)
title = unescapeHTML(self._search_regex( title = self._html_search_regex(
r'<button[^>]+data-showname=(["\'])(?P<title>.*?)\1[^>]*>', webpage, 'title', group='title')) r'<button[^>]+data-showname=(["\'])(?P<title>.+?)\1[^>]*>', webpage, 'title', group='title')
description = unescapeHTML(self._html_search_regex( description = self._html_search_regex(
r'<p>(?P<description>.*?)</p>', webpage, 'description', fatal=False)) r'<p>(?P<description>.+?)</p>', webpage, 'description', fatal=False)
formats = [{ formats = [{
'url': self._html_search_regex( 'url': self._html_search_regex(
r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>.*?)\1[^>]*>', webpage, 'audio_url', group='audio_url'), r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>.+?)\1[^>]*>', webpage, 'audio_url', group='audio_url'),
'ext': 'mp3', 'ext': 'mp3',
'vcodec': 'none',
}] }]
return { return {
'id': episode_id, 'id': episode_id,