[pyvideo] Modernize

This commit is contained in:
Sergey M․ 2014-03-31 19:31:48 +07:00
parent d41ac5f5dc
commit 1cbd410620

View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
import os import os
@ -5,45 +7,50 @@ from .common import InfoExtractor
class PyvideoIE(InfoExtractor): class PyvideoIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)' _VALID_URL = r'http://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
_TESTS = [{
u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes', _TESTS = [
u'file': u'24_4WWkSmNo.mp4', {
u'md5': u'de317418c8bc76b1fd8633e4f32acbc6', 'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
u'info_dict': { 'md5': 'de317418c8bc76b1fd8633e4f32acbc6',
u"title": u"Become a logging expert in 30 minutes", 'info_dict': {
u"description": u"md5:9665350d466c67fb5b1598de379021f7", 'id': '24_4WWkSmNo',
u"upload_date": u"20130320", 'ext': 'mp4',
u"uploader": u"NextDayVideo", 'title': 'Become a logging expert in 30 minutes',
u"uploader_id": u"NextDayVideo", 'description': 'md5:9665350d466c67fb5b1598de379021f7',
'upload_date': '20130320',
'uploader': 'NextDayVideo',
'uploader_id': 'NextDayVideo',
},
'add_ie': ['Youtube'],
}, },
u'add_ie': ['Youtube'], {
}, 'url': 'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
{ 'md5': '5fe1c7e0a8aa5570330784c847ff6d12',
u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v', 'info_dict': {
u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12', 'id': '2542',
u'info_dict': { 'ext': 'm4v',
u'id': u'2542', 'title': 'Gloriajw-SpotifyWithErikBernhardsson182',
u'ext': u'm4v', },
u'title': u'Gloriajw-SpotifyWithErikBernhardsson182',
}, },
},
] ]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
webpage = self._download_webpage(url, video_id)
m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
if m_youtube is not None: if m_youtube is not None:
return self.url_result(m_youtube.group(1), 'Youtube') return self.url_result(m_youtube.group(1), 'Youtube')
title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>', title = self._html_search_regex(
webpage, u'title', flags=re.DOTALL) r'<div class="section">.*?<h3>([^>]+?)</h3>', webpage, 'title', flags=re.DOTALL)
video_url = self._search_regex([r'<source src="(.*?)"', video_url = self._search_regex(
r'<dt>Download</dt>.*?<a href="(.+?)"'], [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'],
webpage, u'video url', flags=re.DOTALL) webpage, 'video url', flags=re.DOTALL)
return { return {
'id': video_id, 'id': video_id,
'title': os.path.splitext(title)[0], 'title': os.path.splitext(title)[0],