Prepare for upload.

[youtubedl] / youtube_dl / extractor / escapist.py

diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py
index 86b145bca9d9da95024525be3f4b5cf441b36b58..c85b4c458d95882f56675fa135aab1f3492b6194 100644 (file)
--- a/youtube_dl/extractor/escapist.py
+++ b/youtube_dl/extractor/escapist.py
@@ -1,68 +1,107 @@
+from __future__ import unicode_literals
+
 import json
-import re
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_str,
-    compat_urllib_parse,
+from ..compat import compat_urllib_request
 
-    ExtractorError,
+from ..utils import (
+    determine_ext,
+    clean_html,
+    int_or_none,
+    float_or_none,
 )
 
 
-class EscapistIE(InfoExtractor):
-    _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        showName = mobj.group('showname')
-        videoId = mobj.group('episode')
-
-        self.report_extraction(videoId)
-        webpage = self._download_webpage(url, videoId)
-
-        videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
-            webpage, u'description', fatal=False)
+def _decrypt_config(key, string):
+    a = ''
+    i = ''
+    r = ''
 
-        imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
-            webpage, u'thumbnail', fatal=False)
+    while len(a) < (len(string) / 2):
+        a += key
 
-        playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
-            webpage, u'player url')
+    a = a[0:int(len(string) / 2)]
 
-        title = self._html_search_regex('<meta name="title" content="([^"]*)"',
-            webpage, u'player url').split(' : ')[-1]
+    t = 0
+    while t < len(string):
+        i += chr(int(string[t] + string[t + 1], 16))
+        t += 2
 
-        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
-        configUrl = compat_urllib_parse.unquote(configUrl)
+    icko = [s for s in i]
 
-        configJSON = self._download_webpage(configUrl, videoId,
-                                            u'Downloading configuration',
-                                            u'unable to download configuration')
+    for t, c in enumerate(a):
+        r += chr(ord(c) ^ ord(icko[t]))
 
-        # Technically, it's JavaScript, not JSON
-        configJSON = configJSON.replace("'", '"')
+    return r
 
-        try:
-            config = json.loads(configJSON)
-        except (ValueError,) as err:
-            raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
 
-        playlist = config['playlist']
-        videoUrl = playlist[1]['url']
-
-        info = {
-            'id': videoId,
-            'url': videoUrl,
-            'uploader': showName,
-            'upload_date': None,
-            'title': title,
+class EscapistIE(InfoExtractor):
+    _VALID_URL = r'https?://?(?:www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
+    _TESTS = [{
+        'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
+        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
+        'info_dict': {
+            'id': '6618',
+            'ext': 'mp4',
+            'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
+            'title': "Breaking Down Baldur's Gate",
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 264,
+            'uploader': 'The Escapist',
+        }
+    }, {
+        'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
+        'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf',
+        'info_dict': {
+            'id': '10044',
             'ext': 'mp4',
-            'thumbnail': imgUrl,
-            'description': videoDesc,
-            'player_url': playerUrl,
+            'description': 'This week, Zero Punctuation reviews Evolve.',
+            'title': 'Evolve - One vs Multiplayer',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 304,
+            'uploader': 'The Escapist',
         }
+    }]
 
-        return [info]
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        ims_video = self._parse_json(
+            self._search_regex(
+                r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
+            video_id)
+        video_id = ims_video['videoID']
+        key = ims_video['hash']
+
+        config_req = compat_urllib_request.Request(
+            'http://www.escapistmagazine.com/videos/'
+            'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
+        config_req.add_header('Referer', url)
+        config = self._download_webpage(config_req, video_id, 'Downloading video config')
+
+        data = json.loads(_decrypt_config(key, config))
+
+        video_data = data['videoData']
+
+        title = clean_html(video_data['title'])
+        duration = float_or_none(video_data.get('duration'), 1000)
+        uploader = video_data.get('publisher')
+
+        formats = [{
+            'url': video['src'],
+            'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']),
+            'height': int_or_none(video.get('res')),
+        } for video in data['files']['videos']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+            'duration': duration,
+            'uploader': uploader,
+        }