1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-24 10:33:45 +01:00
yt-dlp/youtube_dl/extractor/viddler.py
2013-11-03 15:49:59 +01:00

65 lines
2.1 KiB
Python

import json
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
)
class ViddlerIE(InfoExtractor):
_VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
_TEST = {
u"url": u"http://www.viddler.com/v/43903784",
u'file': u'43903784.mp4',
u'md5': u'fbbaedf7813e514eb7ca30410f439ac9',
u'info_dict': {
u"title": u"Video Made Easy",
u"uploader": u"viddler",
u"duration": 100.89,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
embed_url = mobj.group('domain') + u'/embed/' + video_id
webpage = self._download_webpage(embed_url, video_id)
video_sources_code = self._search_regex(
r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs')
video_sources = json.loads(video_sources_code.replace("'", '"'))
formats = [{
'url': video_url,
'format': format_id,
} for video_url, format_id in video_sources.items()]
title = self._html_search_regex(
r"title\s*:\s*'([^']*)'", webpage, u'title')
uploader = self._html_search_regex(
r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False)
duration_s = self._html_search_regex(
r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False)
duration = float(duration_s) if duration_s else None
thumbnail = self._html_search_regex(
r"thumbnail\s*:\s*'([^']*)'",
webpage, u'thumbnail', fatal=False)
info = {
'_type': 'video',
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'uploader': uploader,
'duration': duration,
'formats': formats,
}
# TODO: Remove when #980 has been merged
info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url'])
info.update(info['formats'][-1])
return info