[spankwire] Simplify and properly format

youtube_dl/extractor/spankwire.py

@@ -18,6 +18,7 @@ from ..aes import aes_decrypt_text
 class SpankwireIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
     _TESTS = [{
+        # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
         'md5': '8bbfde12b101204b39e4b9fe7eb67095',
         'info_dict': {
@@ -30,8 +31,8 @@ class SpankwireIE(InfoExtractor):
             'upload_date': '20070507',
             'age_limit': 18,
         }
-              },
+    }, {
-              {
+        # download URL pattern: */mp4_<format_id>_<video_id>.mp4
         'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
         'md5': '09b3c20833308b736ae8902db2f8d7e6',
         'info_dict': {
@@ -43,7 +44,7 @@ class SpankwireIE(InfoExtractor):
             'uploader_id': '3056053',
             'upload_date': '20150822',
             'age_limit': 18,
-                    }
+        },
     }]
 
     def _real_extract(self, url):
@@ -81,9 +82,10 @@ class SpankwireIE(InfoExtractor):
             r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
             webpage, 'comment count', fatal=False))
 
-        video_urls = list(map(
+        videos = re.findall(
-            compat_urllib_parse_unquote,
+            r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)
-            re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)))
+        heights = [int(video[0]) for video in videos]
+        video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos]))
         if webpage.find('flashvars\.encrypted = "true"') != -1:
             password = self._search_regex(
                 r'flashvars\.video_title = "([^"]+)',
@@ -93,39 +95,22 @@ class SpankwireIE(InfoExtractor):
                 video_urls))
 
         formats = []
-        for video_url in video_urls:
+        for height, video_url in zip(heights, video_urls):
             path = compat_urllib_parse_urlparse(video_url).path
-            format = path.split('/')[4].split('_')[:2]
+            _, quality = path.split('/')[4].split('_')[:2]
-            if format[0] == 'mp4':
+            f = {
-                format_id, quality = format
-                format = "-".join(format)
-                if quality == 'normal':
-                    height = 180
-                elif quality == 'high':
-                    height = 240
-                elif quality == 'ultra':
-                    height = 480
-                elif quality == '720p':
-                    height = 720
-                formats.append({
                 'url': video_url,
-                    'format': format,
                 'height': height,
-                    'format_id': format,
+            }
+            tbr = self._search_regex(r'^(\d+)[Kk]$', quality, 'tbr', default=None)
+            if tbr:
+                f.update({
+                    'tbr': int(tbr),
+                    'format_id': '%dp' % height,
                 })
             else:
-                resolution, bitrate_str = format
+                f['format_id'] = quality
-                format = "-".join(format)
+            formats.append(f)
-                height = int(resolution.rstrip('Pp'))
-                tbr = int(bitrate_str.rstrip('Kk'))
-                formats.append({
-                    'url': video_url,
-                    'resolution': resolution,
-                    'format': format,
-                    'tbr': tbr,
-                    'height': height,
-                    'format_id': format,
-                })
         self._sort_formats(formats)
 
         age_limit = self._rta_search(webpage)