release 2013.02.22

[youtube-dl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index a5196b0aec4bcf626c2c724561d25c95ed3f2799..95bd948438830ca7f98ad82decb722de69319bdf 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -8,6 +8,7 @@ import locale
 import os
 import re
 import sys
 import os
 import re
 import sys

+import traceback

 import zlib
 import email.utils
 import json
 import zlib
 import email.utils
 import json


@@ -154,6 +155,7 @@ std_headers = {
     'Accept-Encoding': 'gzip, deflate',
     'Accept-Language': 'en-us,en;q=0.5',
 }
     'Accept-Encoding': 'gzip, deflate',
     'Accept-Language': 'en-us,en;q=0.5',
 }

+

 def preferredencoding():
     """Get preferred encoding.
 
 def preferredencoding():
     """Get preferred encoding.
 


@@ -187,7 +189,6 @@ else:
         with open(fn, 'w', encoding='utf-8') as f:
             json.dump(obj, f)
 
         with open(fn, 'w', encoding='utf-8') as f:
             json.dump(obj, f)
 

-

 def htmlentity_transform(matchobj):
     """Transforms an HTML entity to a character.
 
 def htmlentity_transform(matchobj):
     """Transforms an HTML entity to a character.
 


@@ -279,6 +280,12 @@ class AttrParser(compat_html_parser.HTMLParser):
             lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]]
         lines[-1] = lines[-1][:self.result[2][1]]
         return '\n'.join(lines).strip()
             lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]]
         lines[-1] = lines[-1][:self.result[2][1]]
         return '\n'.join(lines).strip()

+# Hack for https://github.com/rg3/youtube-dl/issues/662
+if sys.version_info < (2, 7, 3):
+    AttrParser.parse_endtag = (lambda self, i:
+        i + len("</scr'+'ipt>")
+        if self.rawdata[i:].startswith("</scr'+'ipt>")
+        else compat_html_parser.HTMLParser.parse_endtag(self, i))

 
 def get_element_by_id(id, html):
     """Return the content of the tag with the specified ID in the passed HTML document"""
 
 def get_element_by_id(id, html):
     """Return the content of the tag with the specified ID in the passed HTML document"""


@@ -298,7 +305,8 @@ def clean_html(html):
     """Clean an HTML snippet into a readable string"""
     # Newline vs <br />
     html = html.replace('\n', ' ')
     """Clean an HTML snippet into a readable string"""
     # Newline vs <br />
     html = html.replace('\n', ' ')

-    html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html)
+    html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
+    html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)

     # Strip html tags
     html = re.sub('<.*?>', '', html)
     # Replace html entities
     # Strip html tags
     html = re.sub('<.*?>', '', html)
     # Replace html entities


@@ -407,7 +415,32 @@ def encodeFilename(s):
         # match Windows 9x series as well. Besides, NT 4 is obsolete.)
         return s
     else:
         # match Windows 9x series as well. Besides, NT 4 is obsolete.)
         return s
     else:

-        return s.encode(sys.getfilesystemencoding(), 'ignore')
+        encoding = sys.getfilesystemencoding()
+        if encoding is None:
+            encoding = 'utf-8'
+        return s.encode(encoding, 'ignore')
+
+def decodeOption(optval):
+    if optval is None:
+        return optval
+    if isinstance(optval, bytes):
+        optval = optval.decode(preferredencoding())
+
+    assert isinstance(optval, compat_str)
+    return optval
+
+class ExtractorError(Exception):
+    """Error during info extraction."""
+    def __init__(self, msg, tb=None):
+        """ tb, if given, is the original traceback (so that it can be printed out). """
+        super(ExtractorError, self).__init__(msg)
+        self.traceback = tb
+
+    def format_traceback(self):
+        if self.traceback is None:
+            return None
+        return u''.join(traceback.format_tb(self.traceback))
+

 
 class DownloadError(Exception):
     """Download Error exception.
 
 class DownloadError(Exception):
     """Download Error exception.


@@ -434,7 +467,8 @@ class PostProcessingError(Exception):
     This exception may be raised by PostProcessor's .run() method to
     indicate an error in the postprocessing task.
     """
     This exception may be raised by PostProcessor's .run() method to
     indicate an error in the postprocessing task.
     """

-    pass
+    def __init__(self, msg):
+        self.msg = msg

 
 class MaxDownloadsReached(Exception):
     """ --max-downloads limit has been reached. """
 
 class MaxDownloadsReached(Exception):
     """ --max-downloads limit has been reached. """


@@ -465,14 +499,6 @@ class ContentTooShortError(Exception):
         self.downloaded = downloaded
         self.expected = expected
 
         self.downloaded = downloaded
         self.expected = expected
 

-
-class Trouble(Exception):
-    """Trouble helper exception
-
-    This is an exception to be handled with
-    FileDownloader.trouble
-    """
-

 class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     """Handler for HTTP requests and responses.
 
 class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     """Handler for HTTP requests and responses.
 


@@ -507,14 +533,19 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
         return ret
 
     def http_request(self, req):
         return ret
 
     def http_request(self, req):

-        for h in std_headers:
+        for h,v in std_headers.items():

             if h in req.headers:
                 del req.headers[h]
             if h in req.headers:
                 del req.headers[h]

-            req.add_header(h, std_headers[h])
+            req.add_header(h, v)

         if 'Youtubedl-no-compression' in req.headers:
             if 'Accept-encoding' in req.headers:
                 del req.headers['Accept-encoding']
             del req.headers['Youtubedl-no-compression']
         if 'Youtubedl-no-compression' in req.headers:
             if 'Accept-encoding' in req.headers:
                 del req.headers['Accept-encoding']
             del req.headers['Youtubedl-no-compression']

+        if 'Youtubedl-user-agent' in req.headers:
+            if 'User-agent' in req.headers:
+                del req.headers['User-agent']
+            req.headers['User-agent'] = req.headers['Youtubedl-user-agent']
+            del req.headers['Youtubedl-user-agent']

         return req
 
     def http_response(self, req, resp):
         return req
 
     def http_response(self, req, resp):