youtube-dl/youtube_dl/extractor/normalboots.py

52 lines
2.3 KiB
Python
Raw Normal View History

2014-02-23 17:28:22 +00:00
# encoding: utf-8
from __future__ import unicode_literals
2014-01-30 17:26:50 +00:00
import re
from .common import InfoExtractor
from ..utils import (
unified_strdate,
)
2014-02-23 17:28:22 +00:00
2014-01-30 17:26:50 +00:00
class NormalbootsIE(InfoExtractor):
2014-02-23 17:28:22 +00:00
_VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
2014-01-30 20:01:35 +00:00
_TEST = {
2014-02-23 17:28:22 +00:00
'url': 'http://normalboots.com/video/home-alone-games-jontron/',
'md5': '8bf6de238915dd501105b44ef5f1e0f6',
'info_dict': {
'id': 'home-alone-games-jontron',
'ext': 'mp4',
'title': 'Home Alone Games - JonTron - NormalBoots',
'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for Tense Battle Theme:\xa0http://www.youtube.com/Kiamet/',
'uploader': 'JonTron',
'upload_date': '20140125',
2014-01-30 20:01:35 +00:00
}
}
2014-02-23 17:28:22 +00:00
2014-01-30 17:26:50 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
2014-02-23 17:28:22 +00:00
2014-01-30 17:26:50 +00:00
webpage = self._download_webpage(url, video_id)
video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
2014-11-23 20:39:15 +00:00
webpage, 'uploader')
2014-02-23 17:28:22 +00:00
raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
2014-11-23 20:39:15 +00:00
webpage, 'date')
2014-01-30 17:26:50 +00:00
video_upload_date = unified_strdate(raw_upload_date)
2014-02-23 17:28:22 +00:00
2014-01-30 17:26:50 +00:00
player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
player_page = self._download_webpage(player_url, video_id)
2014-02-23 17:06:51 +00:00
video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
2014-02-23 17:28:22 +00:00
return {
'id': video_id,
'url': video_url,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'uploader': video_uploader,
'upload_date': video_upload_date,
}