[mtv] Check for geo-blocked videos in the xml document, not in the xml’s string

Allows to use the `_download_xml` method
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-01-21 19:57:38 +01:00
parent ef9f2ba7af
commit e4f320a4d0

View file

@ -1,7 +1,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import xml.etree.ElementTree
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
@ -36,10 +35,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
else: else:
return thumb_node.attrib['url'] return thumb_node.attrib['url']
def _extract_video_formats(self, metadataXml): def _extract_video_formats(self, mdoc):
if '/error_country_block.swf' in metadataXml: if re.match(r'.*/error_country_block\.swf$', mdoc.find('.//src').text) is not None:
raise ExtractorError('This video is not available from your country.', expected=True) raise ExtractorError('This video is not available from your country.', expected=True)
mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))
formats = [] formats = []
for rendition in mdoc.findall('.//rendition'): for rendition in mdoc.findall('.//rendition'):
@ -65,7 +63,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', 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_doc = self._download_xml(mediagen_url, video_id,
'Downloading video urls') 'Downloading video urls')
description_node = itemdoc.find('description') description_node = itemdoc.find('description')
@ -76,7 +74,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
return { return {
'title': itemdoc.find('title').text, 'title': itemdoc.find('title').text,
'formats': self._extract_video_formats(mediagen_page), 'formats': self._extract_video_formats(mediagen_doc),
'id': video_id, 'id': video_id,
'thumbnail': self._get_thumbnail_url(uri, itemdoc), 'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description, 'description': description,