Merge remote-tracking branch 'rzhxeo/youporn-hd'

[youtube-dl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index ee8df6a5b844054287d1e6a78668e23746058abd..b3d0f64ea9162876f5cd3d517ef77a9b631c781e 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1,19 +1,20 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+import datetime
+import email.utils
 import errno
 import gzip
 import io
 import json
 import locale
 import os
+import platform
 import re
+import socket
 import sys
 import traceback
 import zlib
-import email.utils
-import socket
-import datetime
 
 try:
     import urllib.request as compat_urllib_request
@@ -60,6 +61,11 @@ try:
 except ImportError: # Python 2
     import httplib as compat_http_client
 
+try:
+    from urllib.error import HTTPError as compat_HTTPError
+except ImportError:  # Python 2
+    from urllib2 import HTTPError as compat_HTTPError
+
 try:
     from subprocess import DEVNULL
     compat_subprocess_get_DEVNULL = lambda: DEVNULL
@@ -489,7 +495,7 @@ def make_HTTPS_handler(opts):
 
 class ExtractorError(Exception):
     """Error during info extraction."""
-    def __init__(self, msg, tb=None, expected=False):
+    def __init__(self, msg, tb=None, expected=False, cause=None):
         """ tb, if given, is the original traceback (so that it can be printed out).
         If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
         """
@@ -497,11 +503,12 @@ class ExtractorError(Exception):
         if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
             expected = True
         if not expected:
-            msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output.'
+            msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output. Make sure you are using the latest version; type  youtube-dl -U  to update.'
         super(ExtractorError, self).__init__(msg)
 
         self.traceback = tb
         self.exc_info = sys.exc_info()  # preserve original exception
+        self.cause = cause
 
     def format_traceback(self):
         if self.traceback is None:
@@ -622,8 +629,23 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
         old_resp = resp
         # gzip
         if resp.headers.get('Content-encoding', '') == 'gzip':
-            gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r')
-            resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+            content = resp.read()
+            gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb')
+            try:
+                uncompressed = io.BytesIO(gz.read())
+            except IOError as original_ioerror:
+                # There may be junk add the end of the file
+                # See http://stackoverflow.com/q/4928560/35070 for details
+                for i in range(1, 1024):
+                    try:
+                        gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb')
+                        uncompressed = io.BytesIO(gz.read())
+                    except IOError:
+                        continue
+                    break
+                else:
+                    raise original_ioerror
+            resp = self.addinfourl_wrapper(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
             resp.msg = old_resp.msg
         # deflate
         if resp.headers.get('Content-encoding', '') == 'deflate':
@@ -657,6 +679,9 @@ def determine_ext(url, default_ext=u'unknown_video'):
     else:
         return default_ext
 
+def subtitles_filename(filename, sub_lang, sub_format):
+    return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
+
 def date_from_str(date_str):
     """
     Return a datetime object from a string in the format YYYYMMDD or
@@ -710,6 +735,16 @@ class DateRange(object):
         return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())
 
 
+def platform_name():
+    """ Returns the platform name as a compat_str """
+    res = platform.platform()
+    if isinstance(res, bytes):
+        res = res.decode(preferredencoding())
+
+    assert isinstance(res, compat_str)
+    return res
+
+
 def bytes_to_intlist(bs):
     if not bs:
         return []
@@ -718,6 +753,7 @@ def bytes_to_intlist(bs):
     else:
         return [ord(c) for c in bs]
 
+
 def intlist_to_bytes(xs):
     if not xs:
         return b''