[Lecture2Go] Add new extractor

[youtube-dl] / youtube_dl / extractor / grooveshark.py

diff --git a/youtube_dl/extractor/grooveshark.py b/youtube_dl/extractor/grooveshark.py
index 1f2c65afe2e3524b7c23f1fadbd12a11af07193d..36ad4915c5e7ea47feec8d32317ec15845a5b7d0 100644 (file)
--- a/youtube_dl/extractor/grooveshark.py
+++ b/youtube_dl/extractor/grooveshark.py
@@ -3,18 +3,18 @@ from __future__ import unicode_literals
 
 import time
 import math
+import os.path
 import re
 
-from urllib import quote, urlencode
-from os.path import basename
 
 from .common import InfoExtractor
-from ..utils import ExtractorError, compat_urllib_request, compat_html_parser
-
-from ..utils import compat_urlparse
-
-urlunparse = compat_urlparse.urlunparse
-urldefrag = compat_urlparse.urldefrag
+from ..compat import (
+    compat_html_parser,
+    compat_urllib_parse,
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import ExtractorError
 
 
 class GroovesharkHtmlParser(compat_html_parser.HTMLParser):
@@ -47,7 +47,7 @@ class GroovesharkIE(InfoExtractor):
     _VALID_URL = r'https?://(www\.)?grooveshark\.com/#!/s/([^/]+)/([^/]+)'
     _TEST = {
         'url': 'http://grooveshark.com/#!/s/Jolene+Tenth+Key+Remix+Ft+Will+Sessions/6SS1DW?src=5',
-        'md5': 'bbccc50b19daca23b8f961152c1dc95b',
+        'md5': '7ecf8aefa59d6b2098517e1baa530023',
         'info_dict': {
             'id': '6SS1DW',
             'title': 'Jolene (Tenth Key Remix ft. Will Sessions)',
@@ -62,28 +62,28 @@ class GroovesharkIE(InfoExtractor):
     def _parse_target(self, target):
         uri = compat_urlparse.urlparse(target)
         hash = uri.fragment[1:].split('?')[0]
-        token = basename(hash.rstrip('/'))
+        token = os.path.basename(hash.rstrip('/'))
         return (uri, hash, token)
 
     def _build_bootstrap_url(self, target):
         (uri, hash, token) = self._parse_target(target)
-        query = 'getCommunicationToken=1&hash=%s&%d' % (quote(hash, safe=''), self.ts)
-        return (urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
+        query = 'getCommunicationToken=1&hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts)
+        return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
 
     def _build_meta_url(self, target):
         (uri, hash, token) = self._parse_target(target)
-        query = 'hash=%s&%d' % (quote(hash, safe=''), self.ts)
-        return (urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
+        query = 'hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts)
+        return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
 
     def _build_stream_url(self, meta):
-        return urlunparse(('http', meta['streamKey']['ip'], '/stream.php', None, None, None))
+        return compat_urlparse.urlunparse(('http', meta['streamKey']['ip'], '/stream.php', None, None, None))
 
     def _build_swf_referer(self, target, obj):
         (uri, _, _) = self._parse_target(target)
-        return urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None))
+        return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None))
 
     def _transform_bootstrap(self, js):
-        return re.split('(?m)^\s*try\s*{', js)[0] \
+        return re.split('(?m)^\s*try\s*\{', js)[0] \
                  .split(' = ', 1)[1].strip().rstrip(';')
 
     def _transform_meta(self, js):
@@ -93,7 +93,7 @@ class GroovesharkIE(InfoExtractor):
         (meta_url, token) = self._build_meta_url(target)
         self.to_screen('Metadata URL: %s' % meta_url)
 
-        headers = {'Referer': urldefrag(target)[0]}
+        headers = {'Referer': compat_urlparse.urldefrag(target)[0]}
         req = compat_urllib_request.Request(meta_url, headers=headers)
         res = self._download_json(req, token,
                                   transform_source=self._transform_meta)
@@ -112,7 +112,7 @@ class GroovesharkIE(InfoExtractor):
     def _get_bootstrap(self, target):
         (bootstrap_url, token) = self._build_bootstrap_url(target)
 
-        headers = {'Referer': urldefrag(target)[0]}
+        headers = {'Referer': compat_urlparse.urldefrag(target)[0]}
         req = compat_urllib_request.Request(bootstrap_url, headers=headers)
         res = self._download_json(req, token, fatal=False,
                                   note='Downloading player bootstrap data',
@@ -123,7 +123,6 @@ class GroovesharkIE(InfoExtractor):
     def _get_playerpage(self, target):
         (_, _, token) = self._parse_target(target)
 
-
         webpage = self._download_webpage(
             target, token,
             note='Downloading player page',
@@ -141,9 +140,9 @@ class GroovesharkIE(InfoExtractor):
 
         if webpage is not None:
             o = GroovesharkHtmlParser.extract_object_tags(webpage)
-            return (webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed'])
+            return webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed']
 
-        return (webpage, None)
+        return webpage, None
 
     def _real_initialize(self):
         self.ts = int(time.time() * 1000)  # timestamp in millis
@@ -155,7 +154,7 @@ class GroovesharkIE(InfoExtractor):
         swf_referer = None
         if self.do_playerpage_request:
             (_, player_objs) = self._get_playerpage(url)
-            if player_objs is not None:
+            if player_objs:
                 swf_referer = self._build_swf_referer(url, player_objs[0])
                 self.to_screen('SWF Referer: %s' % swf_referer)
 
@@ -171,7 +170,7 @@ class GroovesharkIE(InfoExtractor):
         stream_url = self._build_stream_url(meta)
         duration = int(math.ceil(float(meta['streamKey']['uSecs']) / 1000000))
         post_dict = {'streamKey': meta['streamKey']['streamKey']}
-        post_data = urlencode(post_dict).encode('utf-8')
+        post_data = compat_urllib_parse.urlencode(post_dict).encode('utf-8')
         headers = {
             'Content-Length': len(post_data),
             'Content-Type': 'application/x-www-form-urlencoded'