Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-23 00:54:31 +01:00
Code Issues Releases Wiki Activity

[liveleak] Add support for prochan embeds (Fixes #2406)

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-02-19 01:27:12 +01:00
parent c377110539
commit 572a89cc4e
1 changed files with 45 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
youtube_dl/extractor/liveleak.py
View File

@ -4,15 +4,17 @@ import json
import re
from .common import InfoExtractor
from ..utils import int_or_none
class LiveLeakIE(InfoExtractor):
_VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
_TESTS = [{
'url': 'http://www.liveleak.com/view?i=757_1364311680',
'file': '757_1364311680.mp4',
'md5': '0813c2430bea7a46bf13acf3406992f4',
'info_dict': {
'id': '757_1364311680',
'ext': 'mp4',
'description': 'extremely bad day for this guy..!',
'uploader': 'ljfriel2',
'title': 'Most unlucky car accident'
@ -20,25 +22,62 @@ class LiveLeakIE(InfoExtractor):
},
{
'url': 'http://www.liveleak.com/view?i=f93_1390833151',
'file': 'f93_1390833151.mp4',
'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
'info_dict': {
'id': 'f93_1390833151',
'ext': 'mp4',
'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
'uploader': 'ARD_Stinkt',
'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
}
},
{
'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
'md5': '42c6d97d54f1db107958760788c5f48f',
'info_dict': {
'id': '4f7_1392687779',
'ext': 'mp4',
'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing... I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
'uploader': 'CapObveus',
'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
'age_limit': 18,
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id)
video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
video_description = self._og_search_description(webpage)
video_uploader = self._html_search_regex(
r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
age_limit = int_or_none(self._search_regex(
r'you confirm that you are ([0-9]+) years and over.',
webpage, 'age limit', default=None))
sources_raw = self._search_regex(
r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
if sources_raw is None:
sources_raw = '[{ %s}]' % (
self._search_regex(r'(file: ".*?"),', webpage, 'video URL'))
alt_source = self._search_regex(
r'(file: ".*?"),', webpage, 'video URL', default=None)
if alt_source:
sources_raw = '[{ %s}]' % alt_source
else:
# Maybe an embed?
embed_url = self._search_regex(
r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
webpage, 'embed URL')
return {
'_type': 'url_transparent',
'url': embed_url,
'id': video_id,
'title': video_title,
'description': video_description,
'uploader': video_uploader,
'age_limit': age_limit,
}
sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
sources = json.loads(sources_json)
@ -49,15 +88,11 @@ class LiveLeakIE(InfoExtractor):
} for s in sources]
self._sort_formats(formats)
video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
video_description = self._og_search_description(webpage)
video_uploader = self._html_search_regex(
r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
return {
'id': video_id,
'title': video_title,
'description': video_description,
'uploader': video_uploader,
'formats': formats,
'age_limit': age_limit,
}