youtube-dl/youtube_dl/extractor/liveleak.py

106 lines
4.1 KiB
Python
Raw Normal View History

2014-01-28 20:57:38 +00:00
from __future__ import unicode_literals
import json
2013-06-23 20:23:19 +00:00
import re
from .common import InfoExtractor
from ..utils import int_or_none
2013-06-23 20:23:19 +00:00
class LiveLeakIE(InfoExtractor):
2015-01-23 16:09:26 +00:00
_VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'
2014-01-30 05:09:06 +00:00
_TESTS = [{
2014-01-28 20:57:38 +00:00
'url': 'http://www.liveleak.com/view?i=757_1364311680',
'md5': '50f79e05ba149149c1b4ea961223d5b3',
2014-01-28 20:57:38 +00:00
'info_dict': {
'id': '757_1364311680',
'ext': 'flv',
2014-01-28 20:57:38 +00:00
'description': 'extremely bad day for this guy..!',
'uploader': 'ljfriel2',
'title': 'Most unlucky car accident'
2013-06-27 18:46:46 +00:00
}
2014-11-23 20:20:46 +00:00
}, {
2014-01-30 05:09:06 +00:00
'url': 'http://www.liveleak.com/view?i=f93_1390833151',
'md5': 'b13a29626183c9d33944e6a04f41aafc',
2014-01-30 05:09:06 +00:00
'info_dict': {
'id': 'f93_1390833151',
'ext': 'mp4',
2014-01-30 05:09:06 +00:00
'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)',
}
2014-11-23 20:20:46 +00:00
}, {
'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,
}
2014-01-30 05:09:06 +00:00
}]
2013-06-23 20:23:19 +00:00
def _real_extract(self, url):
2015-01-23 16:09:26 +00:00
video_id = self._match_id(url)
2013-06-23 20:23:19 +00:00
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(
2014-01-30 05:09:06 +00:00
r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
if sources_raw is None:
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,
}
2014-01-30 05:09:06 +00:00
sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
sources = json.loads(sources_json)
formats = [{
'format_id': '%s' % i,
'format_note': s.get('label'),
'url': s['file'],
} for i, s in enumerate(sources)]
for i, s in enumerate(sources):
orig_url = s['file'].replace('.h264_base.mp4', '')
if s['file'] != orig_url:
formats.append({
'format_id': 'original-%s' % i,
'format_note': s.get('label'),
'url': orig_url,
'preference': 1,
})
self._sort_formats(formats)
2013-06-23 20:23:19 +00:00
2014-01-28 20:57:38 +00:00
return {
'id': video_id,
2013-06-23 20:23:19 +00:00
'title': video_title,
'description': video_description,
'uploader': video_uploader,
'formats': formats,
'age_limit': age_limit,
2013-06-23 20:23:19 +00:00
}