aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/normalboots.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2014-02-23 18:28:22 +0100
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2014-02-23 18:28:22 +0100
commit92661c994b4f01bb39204d05652f57e7f6491579 (patch)
treeed69515bdcf048bb760a12f0d6b4fe1fb30e07d2 /youtube_dl/extractor/normalboots.py
parentffe8fe356a14e38ab8b5e8329fce015d93b93bc8 (diff)
[normalboots] Modernize and simplify
Diffstat (limited to 'youtube_dl/extractor/normalboots.py')
-rw-r--r--youtube_dl/extractor/normalboots.py66
1 files changed, 28 insertions, 38 deletions
diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py
index 1dce5430f..25e71a56e 100644
--- a/youtube_dl/extractor/normalboots.py
+++ b/youtube_dl/extractor/normalboots.py
@@ -1,61 +1,51 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
from ..utils import (
- ExtractorError,
unified_strdate,
)
+
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 = {
- u'url': u'http://normalboots.com/video/home-alone-games-jontron/',
- u'file': u'home-alone-games-jontron.mp4',
- u'md5': u'8bf6de238915dd501105b44ef5f1e0f6',
- u'info_dict': {
- u'title': u'Home Alone Games - JonTron - NormalBoots',
- 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/',
- u'uploader': u'JonTron',
- u'upload_date': u'20140125',
+ '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',
}
}
-
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
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)
- 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>',
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')
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_page = self._download_webpage(player_url, video_id)
video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
-
- info['url'] = video_url
- info['title'] = video_title
- info['description'] = video_description
- info['thumbnail'] = video_thumbnail
- info['uploader'] = video_uploader
- info['upload_date'] = video_upload_date
-
- return info
+
+ 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,
+ }