Merge pull request #3 from unit193/master

[youtubedl] / youtube_dl / extractor / normalboots.py

diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py
index 3d35b11ac81286a359a06620d0e08e8fae18043b..61fe571dfea17a3fab3206eb6eea0b7a2cbb979b 100644 (file)
--- a/youtube_dl/extractor/normalboots.py
+++ b/youtube_dl/extractor/normalboots.py
@@ -1,9 +1,8 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from .jwplatform import JWPlatformIE

 
 from ..utils import (
     unified_strdate,
 
 from ..utils import (
     unified_strdate,


@@ -11,10 +10,9 @@ from ..utils import (
 
 
 class NormalbootsIE(InfoExtractor):
 
 
 class NormalbootsIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
+    _VALID_URL = r'https?://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$'

     _TEST = {
         'url': 'http://normalboots.com/video/home-alone-games-jontron/',
     _TEST = {
         'url': 'http://normalboots.com/video/home-alone-games-jontron/',

-        'md5': '8bf6de238915dd501105b44ef5f1e0f6',

         'info_dict': {
             'id': 'home-alone-games-jontron',
             'ext': 'mp4',
         'info_dict': {
             'id': 'home-alone-games-jontron',
             'ext': 'mp4',


@@ -22,27 +20,32 @@ class NormalbootsIE(InfoExtractor):
             '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',
             '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': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['JWPlatform'],

     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-
+        video_id = self._match_id(url)

         webpage = self._download_webpage(url, video_id)
         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')
-        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)

 
 

-        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')
+        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))
+
+        jwplatform_url = JWPlatformIE._extract_url(webpage)

 
         return {
 
         return {

+            '_type': 'url_transparent',

             'id': video_id,
             'id': video_id,

-            'url': video_url,
+            'url': jwplatform_url,
+            'ie_key': JWPlatformIE.ie_key(),

             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),