1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-18 10:30:03 +01:00
youtube-dl/youtube_dl/extractor/normalboots.py
2015-02-02 23:38:45 +01:00

57 lines
2.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# encoding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
unified_strdate,
)
class NormalbootsIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$'
_TEST = {
'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',
},
'params': {
# rtmp download
'skip_download': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
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>',
webpage, 'uploader', fatal=False)
video_upload_date = unified_strdate(self._html_search_regex(
r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
webpage, 'date', fatal=False))
player_url = self._html_search_regex(
r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"',
webpage, 'player url')
player_page = self._download_webpage(player_url, video_id)
video_url = self._html_search_regex(
r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
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,
}