diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-03-31 19:31:48 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-03-31 19:31:48 +0700 |
commit | 1cbd4106201fe9b3890932c5a099892b0a05db19 (patch) | |
tree | 4cf1c6c78cdec12596f59f30888277af6a442a79 | |
parent | d41ac5f5dcff6161a094839e54b3b26c1286f90b (diff) |
[pyvideo] Modernize
-rw-r--r-- | youtube_dl/extractor/pyvideo.py | 61 |
1 files changed, 34 insertions, 27 deletions
diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py index 33054591b..d2d909136 100644 --- a/youtube_dl/extractor/pyvideo.py +++ b/youtube_dl/extractor/pyvideo.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import os @@ -5,45 +7,50 @@ from .common import InfoExtractor class PyvideoIE(InfoExtractor): - _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', - u'file': u'24_4WWkSmNo.mp4', - u'md5': u'de317418c8bc76b1fd8633e4f32acbc6', - u'info_dict': { - u"title": u"Become a logging expert in 30 minutes", - u"description": u"md5:9665350d466c67fb5b1598de379021f7", - u"upload_date": u"20130320", - u"uploader": u"NextDayVideo", - u"uploader_id": u"NextDayVideo", + _VALID_URL = r'http://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)' + + _TESTS = [ + { + 'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes', + 'md5': 'de317418c8bc76b1fd8633e4f32acbc6', + 'info_dict': { + 'id': '24_4WWkSmNo', + 'ext': 'mp4', + 'title': 'Become a logging expert in 30 minutes', + 'description': 'md5:9665350d466c67fb5b1598de379021f7', + 'upload_date': '20130320', + 'uploader': 'NextDayVideo', + 'uploader_id': 'NextDayVideo', + }, + 'add_ie': ['Youtube'], }, - u'add_ie': ['Youtube'], - }, - { - u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v', - u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12', - u'info_dict': { - u'id': u'2542', - u'ext': u'm4v', - u'title': u'Gloriajw-SpotifyWithErikBernhardsson182', + { + 'url': 'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v', + 'md5': '5fe1c7e0a8aa5570330784c847ff6d12', + 'info_dict': { + 'id': '2542', + 'ext': 'm4v', + 'title': 'Gloriajw-SpotifyWithErikBernhardsson182', + }, }, - }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) - m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage) + m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage) if m_youtube is not None: return self.url_result(m_youtube.group(1), 'Youtube') - title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>', - webpage, u'title', flags=re.DOTALL) - video_url = self._search_regex([r'<source src="(.*?)"', - r'<dt>Download</dt>.*?<a href="(.+?)"'], - webpage, u'video url', flags=re.DOTALL) + title = self._html_search_regex( + r'<div class="section">.*?<h3>([^>]+?)</h3>', webpage, 'title', flags=re.DOTALL) + video_url = self._search_regex( + [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'], + webpage, 'video url', flags=re.DOTALL) + return { 'id': video_id, 'title': os.path.splitext(title)[0], |