Merge pull request #453 from bigg215/master

Fixed 'title' KeyError and 403 forbidden issues on signed videos

pytube/__main__.py

@@ -117,6 +117,20 @@ class YouTube(object):
                 self.watch_html,
             )['args']
 
+            # Fix for KeyError: 'title' issue #434
+            if 'title' not in self.player_config_args:
+            	try:
+            		from bs4 import BeautifulSoup
+            		soup = BeautifulSoup(self.watch_html, 'lxml')
+            		title = soup.title.get_text().strip()
+            	except ModuleNotFoundError:
+            		i_start = self.watch_html.lower().index('<title>') + len('<title>')
+            		i_end = self.watch_html.lower().index('</title>')
+            		title = self.watch_html[i_start:i_end].strip()
+            	index = title.lower().rfind(' - youtube')
+            	title = title[:index] if index > 0 else title
+            	self.player_config_args['title'] = title
+
         self.vid_descr = extract.get_vid_descr(self.watch_html)
         # https://github.com/nficano/pytube/issues/165
         stream_maps = ['url_encoded_fmt_stream_map']

pytube/cipher.py

@@ -35,14 +35,22 @@ def get_initial_function_name(js):
 
     """
     # c&&d.set("signature", EE(c));
+
+    #403 Forbidden fix.
     pattern = [
-        r'yt\.akamaized\.net/\)\s*\|\|\s*'
-        r'.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent'
-        r'\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
+        r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+        r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+        r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
+        r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
         r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
-        r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent'
-        r'\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
+        r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<si$',
+        r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+        r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+        r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+        r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+        r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('
     ]
+    
     logger.debug('finding initial function name')
     return regex_search(pattern, js, group=1)
 

pytube/mixins.py

@@ -37,8 +37,10 @@ def apply_signature(config_args, fmt, js):
             url = stream['url']
         elif live_stream:
             raise LiveStreamError('Video is currently being streamed live')
-
-        if any([x in url for x in ['signature=', 'sig=']]):
+        #403 Forbidden fix. 
+        if('signature' in url or 
+            ('s' not in stream and 
+            ('&sig=' in url or '&lsig=' in url))):
             # For certain videos, YouTube will just provide them pre-signed, in
             # which case there's no real magic to download them and we can skip
             # the whole signature descrambling entirely.
@@ -61,7 +63,8 @@ def apply_signature(config_args, fmt, js):
                 }, indent=2,
             ),
         )
-        stream_manifest[i]['url'] = url + '&signature=' + signature
+        #403 forbidden fix
+        stream_manifest[i]['url'] = url + '&sig=' + signature
 
 
 def apply_descrambler(stream_data, key):

pytube/request.py

@@ -2,6 +2,8 @@
 """Implements a simple wrapper around urlopen."""
 from pytube.compat import urlopen
 
+#403 forbidden fix
+import urllib.request
 
 def get(
     url=None, headers=False,
@@ -18,7 +20,12 @@ def get(
     :param int chunk_size:
         The size in bytes of each chunk.
     """
-    response = urlopen(url)
+
+    #403 forbidden fix
+    req = urllib.request.Request(url, headers = {"User-Agent": "Mozilla/5.0"})
+    #response = urlopen(url)
+    response = urlopen(req)
+    
     if streaming:
         return stream_response(response, chunk_size)
     elif headers: