youtube-dl

commit 5196b988971716b9e9c5884d33c757a41aa4548a
parent e6e63e91a70a9c2e4ab92b8afad6fac3b8bede18
Author: Naglis Jonaitis <njonaitis@gmail.com>
Date:   Sat, 30 May 2015 14:16:18 +0300

[tubitv] Add new extractor (Closes #5524)

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/tubitv.py
 | 
79
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 80 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -569,6 +569,7 @@ from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
 from .trutube import TruTubeIE
 from .tube8 import Tube8IE
+from .tubitv import TubiTvIE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tunein import TuneInIE
diff --git a/youtube_dl/extractor/tubitv.py b/youtube_dl/extractor/tubitv.py
@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import codecs
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request
+)
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class TubiTvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tubitv\.com/video\?id=(?P<id>[0-9]+)'
+    _LOGIN_URL = 'http://tubitv.com/login'
+    _NETRC_MACHINE = 'tubitv'
+    _TEST = {
+        'url': 'http://tubitv.com/video?id=54411&title=The_Kitchen_Musical_-_EP01',
+        'info_dict': {
+            'id': '54411',
+            'ext': 'mp4',
+            'title': 'The Kitchen Musical - EP01',
+            'thumbnail': 're:^https?://.*\.png$',
+            'description': 'md5:37532716166069b353e8866e71fefae7',
+            'duration': 2407,
+        },
+        'params': {
+            'skip_download': 'HLS download',
+        },
+    }
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+        self.report_login()
+        form_data = {
+            'username': username,
+            'password': password,
+        }
+        payload = compat_urllib_parse.urlencode(form_data).encode('utf-8')
+        request = compat_urllib_request.Request(self._LOGIN_URL, payload)
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        login_page = self._download_webpage(
+            request, None, False, 'Wrong login info')
+        if not re.search(r'id="tubi-logout"', login_page):
+            raise ExtractorError(
+                'Login failed (invalid username/password)', expected=True)
+
+    def _real_initialize(self):
+        self._login()
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = int_or_none(self._html_search_meta(
+            'video:duration', webpage, 'duration'))
+
+        apu = self._search_regex(r"apu='([^']+)'", webpage, 'apu')
+        m3u8_url = codecs.decode(apu, 'rot_13')[::-1]
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+        }