[xtube] Fix extraction with non-standard JSON 'sources'

Closes #12734

Thanks @paulguy for the fix!
This commit is contained in:
Yen Chi Hsuan 2017-04-29 15:55:08 +08:00
parent e7db6759e4
commit 24eb7c2578
No known key found for this signature in database
GPG key ID: 7F902A182457CA23
2 changed files with 27 additions and 2 deletions

View file

@ -1,3 +1,9 @@
version <unreleased>
Extractors
* [xtube] Fix extraction for older FLV videos (#12734)
version 2017.04.28 version 2017.04.28
Core Core

View file

@ -6,6 +6,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
js_to_json,
orderedSet, orderedSet,
parse_duration, parse_duration,
sanitized_Request, sanitized_Request,
@ -37,6 +38,22 @@ class XTubeIE(InfoExtractor):
'comment_count': int, 'comment_count': int,
'age_limit': 18, 'age_limit': 18,
} }
}, {
# FLV videos with duplicated formats
'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
'md5': 'a406963eb349dd43692ec54631efd88b',
'info_dict': {
'id': '9299752',
'display_id': 'A-Super-Run-Part-1-YT',
'ext': 'flv',
'title': 'A Super Run - Part 1 (YT)',
'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93',
'uploader': 'tshirtguy59',
'duration': 579,
'view_count': int,
'comment_count': int,
'age_limit': 18,
},
}, { }, {
# new URL schema # new URL schema
'url': 'http://www.xtube.com/video-watch/strange-erotica-625837', 'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
@ -68,8 +85,9 @@ class XTubeIE(InfoExtractor):
}) })
sources = self._parse_json(self._search_regex( sources = self._parse_json(self._search_regex(
r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),', r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
webpage, 'sources', group='sources'), video_id) webpage, 'sources', group='sources'), video_id,
transform_source=js_to_json)
formats = [] formats = []
for format_id, format_url in sources.items(): for format_id, format_url in sources.items():
@ -78,6 +96,7 @@ class XTubeIE(InfoExtractor):
'format_id': format_id, 'format_id': format_id,
'height': int_or_none(format_id), 'height': int_or_none(format_id),
}) })
self._remove_duplicate_formats(formats)
self._sort_formats(formats) self._sort_formats(formats)
title = self._search_regex( title = self._search_regex(