Update upstream source from tag 'upstream/2017.11.06'

[youtubedl] / youtube_dl / extractor / teamcoco.py

diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index b2a4b1fc05430558ad9b33a9aa3ce834107dc6e3..75346393b017995098d08136df2cbffad1e1c6bb 100644 (file)
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8

 from __future__ import unicode_literals
 
 import base64
 from __future__ import unicode_literals
 
 import base64


@@ -16,7 +16,7 @@ from ..compat import compat_ord
 
 
 class TeamcocoIE(InfoExtractor):
 
 
 class TeamcocoIE(InfoExtractor):

-    _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
+    _VALID_URL = r'https?://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'

     _TESTS = [
         {
             'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
     _TESTS = [
         {
             'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',


@@ -51,6 +51,17 @@ class TeamcocoIE(InfoExtractor):
             'params': {
                 'skip_download': True,  # m3u8 downloads
             }
             'params': {
                 'skip_download': True,  # m3u8 downloads
             }

+        }, {
+            'url': 'http://teamcoco.com/video/full-episode-mon-6-1-joel-mchale-jake-tapper-and-musical-guest-courtney-barnett?playlist=x;eyJ0eXBlIjoidGFnIiwiaWQiOjl9',
+            'info_dict': {
+                'id': '89341',
+                'ext': 'mp4',
+                'title': 'Full Episode - Mon. 6/1 - Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+                'description': 'Guests: Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+            },
+            'params': {
+                'skip_download': True,  # m3u8 downloads
+            }

         }
     ]
     _VIDEO_ID_REGEXES = (
         }
     ]
     _VIDEO_ID_REGEXES = (


@@ -77,7 +88,7 @@ class TeamcocoIE(InfoExtractor):
         preload_codes = self._html_search_regex(
             r'(function.+)setTimeout\(function\(\)\{playlist',
             webpage, 'preload codes')
         preload_codes = self._html_search_regex(
             r'(function.+)setTimeout\(function\(\)\{playlist',
             webpage, 'preload codes')

-        base64_fragments = re.findall(r'"([a-zA-z0-9+/=]+)"', preload_codes)
+        base64_fragments = re.findall(r'"([a-zA-Z0-9+/=]+)"', preload_codes)

         base64_fragments.remove('init')
 
         def _check_sequence(cur_fragments):
         base64_fragments.remove('init')
 
         def _check_sequence(cur_fragments):


@@ -110,9 +121,23 @@ class TeamcocoIE(InfoExtractor):
         get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
         for filed in data['files']:
             if determine_ext(filed['url']) == 'm3u8':
         get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
         for filed in data['files']:
             if determine_ext(filed['url']) == 'm3u8':

-                formats.extend(self._extract_m3u8_formats(
-                    filed['url'], video_id, ext='mp4'))
+                # compat_urllib_parse.urljoin does not work here
+                if filed['url'].startswith('/'):
+                    m3u8_url = 'http://ht.cdn.turner.com/tbs/big/teamcoco' + filed['url']
+                else:
+                    m3u8_url = filed['url']
+                m3u8_formats = self._extract_m3u8_formats(
+                    m3u8_url, video_id, ext='mp4')
+                for m3u8_format in m3u8_formats:
+                    if m3u8_format not in formats:
+                        formats.append(m3u8_format)
+            elif determine_ext(filed['url']) == 'f4m':
+                # TODO Correct f4m extraction
+                continue

             else:
             else:

+                if filed['url'].startswith('/mp4:protected/'):
+                    # TODO Correct extraction for these files
+                    continue

                 m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
                 if m_format is not None:
                     format_id = m_format.group(1)
                 m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
                 if m_format is not None:
                     format_id = m_format.group(1)