1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-30 02:14:37 +01:00
youtube-dl/youtube_dl/extractor/vidme.py
2015-08-01 04:03:52 +06:00

96 lines
3.3 KiB
Python

from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
float_or_none,
str_to_int,
)
class VidmeIE(InfoExtractor):
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'https://vid.me/QNB',
'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
'info_dict': {
'id': 'QNB',
'ext': 'mp4',
'title': 'Fishing for piranha - the easy way',
'description': 'source: https://www.facebook.com/photo.php?v=312276045600871',
'duration': 119.92,
'timestamp': 1406313244,
'upload_date': '20140725',
'thumbnail': 're:^https?://.*\.jpg',
'view_count': int,
'like_count': int,
},
}, {
# tests uploader field
'url': 'https://vid.me/4Iib',
'info_dict': {
'id': '4Iib',
'ext': 'mp4',
'title': 'The Carver',
'description': 'md5:e9c24870018ae8113be936645b93ba3c',
'duration': 97.859999999999999,
'timestamp': 1433203629,
'upload_date': '20150602',
'uploader': 'Thomas',
'thumbnail': 're:^https?://.*\.jpg',
'view_count': int,
'like_count': int,
},
'params': {
'skip_download': True,
},
}, {
# From http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
'url': 'https://vid.me/e/Wmur',
'only_matching': True,
}]
def _real_extract(self, url):
url = url.replace('vid.me/e/', 'vid.me/')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage, default='')
thumbnail = self._og_search_thumbnail(webpage)
timestamp = int_or_none(self._og_search_property(
'updated_time', webpage, fatal=False))
width = int_or_none(self._og_search_property(
'video:width', webpage, fatal=False))
height = int_or_none(self._og_search_property(
'video:height', webpage, fatal=False))
duration = float_or_none(self._html_search_regex(
r'data-duration="([^"]+)"', webpage, 'duration', fatal=False))
view_count = str_to_int(self._html_search_regex(
r'<(?:li|span) class="video_views">\s*([\d,\.]+)\s*plays?',
webpage, 'view count', fatal=False))
like_count = str_to_int(self._html_search_regex(
r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">',
webpage, 'like count', fatal=False))
uploader = self._html_search_regex(
'class="video_author_username"[^>]*>([^<]+)',
webpage, 'uploader', default=None)
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'width': width,
'height': height,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'uploader': uploader,
}