administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 11:20:41 +00:00
Code Issues Projects Releases Wiki Activity

[empflix] Revert to XML parser

Browse Source 
Don't rely on the XML being broken (if they fix it, our code wouldn't work anymore).
Instead, use the transform function we already have :)

This partially reverts commit c7bee2a725.
This commit is contained in:
Philipp Hagemeister 2014-08-26 15:49:15 +02:00
parent a204c85408
commit 8f1ea7cbb6
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/empflix.py
View File

@ -3,6 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import fix_xml_ampersands
class EmpflixIE(InfoExtractor):
@ -35,20 +36,17 @@ class EmpflixIE(InfoExtractor):
r'flashvars\.config = escape\("([^"]+)"',
webpage, 'flashvars.config')
# XML is malformed
cfg_xml = self._download_webpage(
cfg_url, video_id, note='Downloading metadata')
cfg_xml = self._download_xml(
cfg_url, video_id, note='Downloading metadata',
transform_source=fix_xml_ampersands)
formats = [
{
'url': item[1],
'format_id': item[0],
} for item in re.findall(
r'<item>\s*<res>([^>]+)</res>\s*<videoLink>([^<]+)</videoLink>\s*</item>', cfg_xml)
'url': item.find('videoLink').text,
'format_id': item.find('res').text,
} for item in cfg_xml.findall('./quality/item')
]
thumbnail = self._html_search_regex(
r'<startThumb>([^<]+)</startThumb>', cfg_xml, 'thumbnail', fatal=False)
thumbnail = cfg_xml.find('./startThumb').text
return {
'id': video_id,