X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=768c6207df5e32728c95ccc4a1cfa5e05d9088c3;hb=a921f40799d2ecb4be53b3241d2dbfc80f804d73;hp=f78b5fe7889e6493ed8d87046dd7294fb3e3809f;hpb=2eabb80254f48d63a464247140d8e04a73418ded;p=youtube-dl

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index f78b5fe78..768c6207d 100644
--- 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
@@ -61,7 +62,7 @@ except ImportError: # Python 2
     import httplib as compat_http_client
 
 try:
-    from http.error import HTTPError as compat_HTTPError
+    from urllib.error import HTTPError as compat_HTTPError
 except ImportError:  # Python 2
     from urllib2 import HTTPError as compat_HTTPError
 
@@ -212,7 +213,7 @@ if sys.version_info >= (2,7):
     def find_xpath_attr(node, xpath, key, val):
         """ Find the xpath xpath[@key=val] """
         assert re.match(r'^[a-zA-Z]+$', key)
-        assert re.match(r'^[a-zA-Z@\s]*$', val)
+        assert re.match(r'^[a-zA-Z0-9@\s]*$', val)
         expr = xpath + u"[@%s='%s']" % (key, val)
         return node.find(expr)
 else:
@@ -248,7 +249,17 @@ def htmlentity_transform(matchobj):
     return (u'&%s;' % entity)
 
 compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
-class AttrParser(compat_html_parser.HTMLParser):
+class BaseHTMLParser(compat_html_parser.HTMLParser):
+    def __init(self):
+        compat_html_parser.HTMLParser.__init__(self)
+        self.html = None
+
+    def loads(self, html):
+        self.html = html
+        self.feed(html)
+        self.close()
+
+class AttrParser(BaseHTMLParser):
     """Modified HTMLParser that isolates a tag with the specified attribute"""
     def __init__(self, attribute, value):
         self.attribute = attribute
@@ -256,10 +267,9 @@ class AttrParser(compat_html_parser.HTMLParser):
         self.result = None
         self.started = False
         self.depth = {}
-        self.html = None
         self.watch_startpos = False
         self.error_count = 0
-        compat_html_parser.HTMLParser.__init__(self)
+        BaseHTMLParser.__init__(self)
 
     def error(self, message):
         if self.error_count > 10 or self.started:
@@ -268,11 +278,6 @@ class AttrParser(compat_html_parser.HTMLParser):
         self.error_count += 1
         self.goahead(1)
 
-    def loads(self, html):
-        self.html = html
-        self.feed(html)
-        self.close()
-
     def handle_starttag(self, tag, attrs):
         attrs = dict(attrs)
         if self.started:
@@ -333,6 +338,38 @@ def get_element_by_attribute(attribute, value, html):
         pass
     return parser.get_result()
 
+class MetaParser(BaseHTMLParser):
+    """
+    Modified HTMLParser that isolates a meta tag with the specified name 
+    attribute.
+    """
+    def __init__(self, name):
+        BaseHTMLParser.__init__(self)
+        self.name = name
+        self.content = None
+        self.result = None
+
+    def handle_starttag(self, tag, attrs):
+        if tag != 'meta':
+            return
+        attrs = dict(attrs)
+        if attrs.get('name') == self.name:
+            self.result = attrs.get('content')
+
+    def get_result(self):
+        return self.result
+
+def get_meta_content(name, html):
+    """
+    Return the content attribute from the meta tag with the given name attribute.
+    """
+    parser = MetaParser(name)
+    try:
+        parser.loads(html)
+    except compat_html_parser.HTMLParseError:
+        pass
+    return parser.get_result()
+
 
 def clean_html(html):
     """Clean an HTML snippet into a readable string"""
@@ -628,8 +665,23 @@ 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':
@@ -717,3 +769,31 @@ class DateRange(object):
         return self.start <= date <= self.end
     def __str__(self):
         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 []
+    if isinstance(bs[0], int):  # Python 3
+        return list(bs)
+    else:
+        return [ord(c) for c in bs]
+
+
+def intlist_to_bytes(xs):
+    if not xs:
+        return b''
+    if isinstance(chr(0), bytes):  # Python 2
+        return ''.join([chr(x) for x in xs])
+    else:
+        return bytes(xs)