pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-05 09:57:59 +09:00
Code Issues Projects Releases Wiki Activity

[normalboots] Modernize and simplify

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-23 18:28:22 +01:00
parent ffe8fe356a
commit 92661c994b
1 changed files with 28 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
youtube_dl/extractor/normalboots.py
View File

@ -1,61 +1,51 @@
# encoding: utf-8
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
unified_strdate, unified_strdate,
) )
class NormalbootsIE(InfoExtractor): class NormalbootsIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$' _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
_TEST = { _TEST = {
u'url': u'http://normalboots.com/video/home-alone-games-jontron/', 'url': 'http://normalboots.com/video/home-alone-games-jontron/',
u'file': u'home-alone-games-jontron.mp4', 'md5': '8bf6de238915dd501105b44ef5f1e0f6',
u'md5': u'8bf6de238915dd501105b44ef5f1e0f6', 'info_dict': {
u'info_dict': { 'id': 'home-alone-games-jontron',
u'title': u'Home Alone Games - JonTron - NormalBoots', 'ext': 'mp4',
u'description': u'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 \u2018Tense Battle Theme\u2019:\xa0http://www.youtube.com/Kiamet/', 'title': 'Home Alone Games - JonTron - NormalBoots',
u'uploader': u'JonTron', '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/',
u'upload_date': u'20140125', 'uploader': 'JonTron',
'upload_date': '20140125',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid') video_id = mobj.group('videoid')
info = {
'id': video_id,
'uploader': None,
'upload_date': None,
}
if url[:4] != 'http':
url = 'http://' + url
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_title = self._og_search_title(webpage)
video_description = self._og_search_description(webpage)
video_thumbnail = self._og_search_thumbnail(webpage)
video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>', 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') webpage, 'uploader')
raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
webpage, 'date') webpage, 'date')
video_upload_date = unified_strdate(raw_upload_date) video_upload_date = unified_strdate(raw_upload_date)
video_upload_date = unified_strdate(raw_upload_date)
player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url') 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) player_page = self._download_webpage(player_url, video_id)
video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file') video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
info['url'] = video_url return {
info['title'] = video_title 'id': video_id,
info['description'] = video_description 'url': video_url,
info['thumbnail'] = video_thumbnail 'title': self._og_search_title(webpage),
info['uploader'] = video_uploader 'description': self._og_search_description(webpage),
info['upload_date'] = video_upload_date 'thumbnail': self._og_search_thumbnail(webpage),
'uploader': video_uploader,
return info 'upload_date': video_upload_date,
}