0
0
Fork 0

[mtv] Use unicode_literals

main
Philipp Hagemeister 2014-01-22 00:07:02 +01:00
parent 90834c78fe
commit 32dac6943d
1 changed files with 23 additions and 21 deletions

View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
import xml.etree.ElementTree import xml.etree.ElementTree
@ -38,7 +40,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
def _extract_video_formats(self, metadataXml): def _extract_video_formats(self, metadataXml):
if '/error_country_block.swf' in metadataXml: if '/error_country_block.swf' in metadataXml:
raise ExtractorError(u'This video is not available from your country.', expected=True) raise ExtractorError('This video is not available from your country.', expected=True)
mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8')) mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))
formats = [] formats = []
@ -62,11 +64,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
self.report_extraction(video_id) self.report_extraction(video_id)
mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url'] mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url']
# Remove the templates, like &device={device} # Remove the templates, like &device={device}
mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', u'', mediagen_url) mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
if 'acceptMethods' not in mediagen_url: if 'acceptMethods' not in mediagen_url:
mediagen_url += '&acceptMethods=fms' mediagen_url += '&acceptMethods=fms'
mediagen_page = self._download_webpage(mediagen_url, video_id, mediagen_page = self._download_webpage(mediagen_url, video_id,
u'Downloading video urls') 'Downloading video urls')
description_node = itemdoc.find('description') description_node = itemdoc.find('description')
if description_node is not None: if description_node is not None:
@ -101,7 +103,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
idoc = self._download_xml( idoc = self._download_xml(
self._FEED_URL + '?' + data, video_id, self._FEED_URL + '?' + data, video_id,
u'Downloading info', transform_source=fix_xml_ampersands) 'Downloading info', transform_source=fix_xml_ampersands)
return [self._get_video_info(item) for item in idoc.findall('.//item')] return [self._get_video_info(item) for item in idoc.findall('.//item')]
@ -114,25 +116,25 @@ class MTVIE(MTVServicesInfoExtractor):
_TESTS = [ _TESTS = [
{ {
u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml', 'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
u'file': u'853555.mp4', 'file': '853555.mp4',
u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8', 'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
u'info_dict': { 'info_dict': {
u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"', 'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.', 'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
}, },
}, },
{ {
u'add_ie': ['Vevo'], 'add_ie': ['Vevo'],
u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml', 'url': 'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
u'file': u'USCJY1331283.mp4', 'file': 'USCJY1331283.mp4',
u'md5': u'73b4e7fcadd88929292fe52c3ced8caf', 'md5': '73b4e7fcadd88929292fe52c3ced8caf',
u'info_dict': { 'info_dict': {
u'title': u'Everything Has Changed', 'title': 'Everything Has Changed',
u'upload_date': u'20130606', 'upload_date': '20130606',
u'uploader': u'Taylor Swift', 'uploader': 'Taylor Swift',
}, },
u'skip': u'VEVO is only available in some countries', 'skip': 'VEVO is only available in some countries',
}, },
] ]
@ -151,8 +153,8 @@ class MTVIE(MTVServicesInfoExtractor):
webpage, re.DOTALL) webpage, re.DOTALL)
if m_vevo: if m_vevo:
vevo_id = m_vevo.group(1); vevo_id = m_vevo.group(1);
self.to_screen(u'Vevo video detected: %s' % vevo_id) self.to_screen('Vevo video detected: %s' % vevo_id)
return self.url_result('vevo:%s' % vevo_id, ie='Vevo') return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri') uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri')
return self._get_videos_info(uri) return self._get_videos_info(uri)