Merge tag 'upstream/2013.06.33'

[youtubedl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 2853ba50f228bb1f87900aa78a256b1637fcee2b..4d415bd611ec4020052a3c18cfe5fb6dbd6309fc 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1,354 +1,680 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 

+import errno

 import gzip
 import gzip

-import htmlentitydefs
-import HTMLParser
+import io
+import json

 import locale
 import os
 import re
 import sys
 import locale
 import os
 import re
 import sys

+import traceback

 import zlib
 import zlib

-import urllib2

 import email.utils
 import email.utils

-import json
+import socket
+import datetime
+
+try:
+    import urllib.request as compat_urllib_request
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_request
+
+try:
+    import urllib.error as compat_urllib_error
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_error
+
+try:
+    import urllib.parse as compat_urllib_parse
+except ImportError: # Python 2
+    import urllib as compat_urllib_parse

 
 try:
 
 try:

-       import cStringIO as StringIO
+    from urllib.parse import urlparse as compat_urllib_parse_urlparse
+except ImportError: # Python 2
+    from urlparse import urlparse as compat_urllib_parse_urlparse
+
+try:
+    import http.cookiejar as compat_cookiejar
+except ImportError: # Python 2
+    import cookielib as compat_cookiejar
+
+try:
+    import html.entities as compat_html_entities
+except ImportError: # Python 2
+    import htmlentitydefs as compat_html_entities
+
+try:
+    import html.parser as compat_html_parser
+except ImportError: # Python 2
+    import HTMLParser as compat_html_parser
+
+try:
+    import http.client as compat_http_client
+except ImportError: # Python 2
+    import httplib as compat_http_client
+
+try:
+    from subprocess import DEVNULL
+    compat_subprocess_get_DEVNULL = lambda: DEVNULL

 except ImportError:
 except ImportError:

-       import StringIO
+    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
+
+try:
+    from urllib.parse import parse_qs as compat_parse_qs
+except ImportError: # Python 2
+    # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
+    # Python 2's version is apparently totally broken
+    def _unquote(string, encoding='utf-8', errors='replace'):
+        if string == '':
+            return string
+        res = string.split('%')
+        if len(res) == 1:
+            return string
+        if encoding is None:
+            encoding = 'utf-8'
+        if errors is None:
+            errors = 'replace'
+        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
+        pct_sequence = b''
+        string = res[0]
+        for item in res[1:]:
+            try:
+                if not item:
+                    raise ValueError
+                pct_sequence += item[:2].decode('hex')
+                rest = item[2:]
+                if not rest:
+                    # This segment was just a single percent-encoded character.
+                    # May be part of a sequence of code units, so delay decoding.
+                    # (Stored in pct_sequence).
+                    continue
+            except ValueError:
+                rest = '%' + item
+            # Encountered non-percent-encoded characters. Flush the current
+            # pct_sequence.
+            string += pct_sequence.decode(encoding, errors) + rest
+            pct_sequence = b''
+        if pct_sequence:
+            # Flush the final pct_sequence
+            string += pct_sequence.decode(encoding, errors)
+        return string
+
+    def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
+                encoding='utf-8', errors='replace'):
+        qs, _coerce_result = qs, unicode
+        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
+        r = []
+        for name_value in pairs:
+            if not name_value and not strict_parsing:
+                continue
+            nv = name_value.split('=', 1)
+            if len(nv) != 2:
+                if strict_parsing:
+                    raise ValueError("bad query field: %r" % (name_value,))
+                # Handle case of a control-name with no equal sign
+                if keep_blank_values:
+                    nv.append('')
+                else:
+                    continue
+            if len(nv[1]) or keep_blank_values:
+                name = nv[0].replace('+', ' ')
+                name = _unquote(name, encoding=encoding, errors=errors)
+                name = _coerce_result(name)
+                value = nv[1].replace('+', ' ')
+                value = _unquote(value, encoding=encoding, errors=errors)
+                value = _coerce_result(value)
+                r.append((name, value))
+        return r
+
+    def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
+                encoding='utf-8', errors='replace'):
+        parsed_result = {}
+        pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
+                        encoding=encoding, errors=errors)
+        for name, value in pairs:
+            if name in parsed_result:
+                parsed_result[name].append(value)
+            else:
+                parsed_result[name] = [value]
+        return parsed_result
+
+try:
+    compat_str = unicode # Python 2
+except NameError:
+    compat_str = str
+
+try:
+    compat_chr = unichr # Python 2
+except NameError:
+    compat_chr = chr
+
+def compat_ord(c):
+    if type(c) is int: return c
+    else: return ord(c)
+
+# This is not clearly defined otherwise
+compiled_regex_type = type(re.compile(''))

 
 std_headers = {
 
 std_headers = {

-       'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
-       'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
-       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
-       'Accept-Encoding': 'gzip, deflate',
-       'Accept-Language': 'en-us,en;q=0.5',
+    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
+    'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
+    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+    'Accept-Encoding': 'gzip, deflate',
+    'Accept-Language': 'en-us,en;q=0.5',

 }
 
 def preferredencoding():
 }
 
 def preferredencoding():

-       """Get preferred encoding.
-
-       Returns the best encoding scheme for the system, based on
-       locale.getpreferredencoding() and some further tweaks.
-       """
-       def yield_preferredencoding():
-               try:
-                       pref = locale.getpreferredencoding()
-                       u'TEST'.encode(pref)
-               except:
-                       pref = 'UTF-8'
-               while True:
-                       yield pref
-       return yield_preferredencoding().next()
-
+    """Get preferred encoding.
+
+    Returns the best encoding scheme for the system, based on
+    locale.getpreferredencoding() and some further tweaks.
+    """
+    try:
+        pref = locale.getpreferredencoding()
+        u'TEST'.encode(pref)
+    except:
+        pref = 'UTF-8'
+
+    return pref
+
+if sys.version_info < (3,0):
+    def compat_print(s):
+        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
+else:
+    def compat_print(s):
+        assert type(s) == type(u'')
+        print(s)
+
+# In Python 2.x, json.dump expects a bytestream.
+# In Python 3.x, it writes to a character stream
+if sys.version_info < (3,0):
+    def write_json_file(obj, fn):
+        with open(fn, 'wb') as f:
+            json.dump(obj, f)
+else:
+    def write_json_file(obj, fn):
+        with open(fn, 'w', encoding='utf-8') as f:
+            json.dump(obj, f)

 
 def htmlentity_transform(matchobj):
 
 def htmlentity_transform(matchobj):

-       """Transforms an HTML entity to a Unicode character.
-
-       This function receives a match object and is intended to be used with
-       the re.sub() function.
-       """
-       entity = matchobj.group(1)
-
-       # Known non-numeric HTML entity
-       if entity in htmlentitydefs.name2codepoint:
-               return unichr(htmlentitydefs.name2codepoint[entity])
-
-       # Unicode character
-       mobj = re.match(ur'(?u)#(x?\d+)', entity)
-       if mobj is not None:
-               numstr = mobj.group(1)
-               if numstr.startswith(u'x'):
-                       base = 16
-                       numstr = u'0%s' % numstr
-               else:
-                       base = 10
-               return unichr(long(numstr, base))
-
-       # Unknown entity in name, return its literal representation
-       return (u'&%s;' % entity)
-
-HTMLParser.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 IDParser(HTMLParser.HTMLParser):
-       """Modified HTMLParser that isolates a tag with the specified id"""
-       def __init__(self, id):
-               self.id = id
-               self.result = None
-               self.started = False
-               self.depth = {}
-               self.html = None
-               self.watch_startpos = False
-               self.error_count = 0
-               HTMLParser.HTMLParser.__init__(self)
-
-       def error(self, message):
-               print >> sys.stderr, self.getpos()
-               if self.error_count > 10 or self.started:
-                       raise HTMLParser.HTMLParseError(message, self.getpos())
-               self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
-               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:
-                       self.find_startpos(None)
-               if 'id' in attrs and attrs['id'] == self.id:
-                       self.result = [tag]
-                       self.started = True
-                       self.watch_startpos = True
-               if self.started:
-                       if not tag in self.depth: self.depth[tag] = 0
-                       self.depth[tag] += 1
-
-       def handle_endtag(self, tag):
-               if self.started:
-                       if tag in self.depth: self.depth[tag] -= 1
-                       if self.depth[self.result[0]] == 0:
-                               self.started = False
-                               self.result.append(self.getpos())
-
-       def find_startpos(self, x):
-               """Needed to put the start position of the result (self.result[1])
-               after the opening tag with the requested id"""
-               if self.watch_startpos:
-                       self.watch_startpos = False
-                       self.result.append(self.getpos())
-       handle_entityref = handle_charref = handle_data = handle_comment = \
-       handle_decl = handle_pi = unknown_decl = find_startpos
-
-       def get_result(self):
-               if self.result == None: return None
-               if len(self.result) != 3: return None
-               lines = self.html.split('\n')
-               lines = lines[self.result[1][0]-1:self.result[2][0]]
-               lines[0] = lines[0][self.result[1][1]:]
-               if len(lines) == 1:
-                       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()
+    """Transforms an HTML entity to a character.
+
+    This function receives a match object and is intended to be used with
+    the re.sub() function.
+    """
+    entity = matchobj.group(1)
+
+    # Known non-numeric HTML entity
+    if entity in compat_html_entities.name2codepoint:
+        return compat_chr(compat_html_entities.name2codepoint[entity])
+
+    mobj = re.match(u'(?u)#(x?\\d+)', entity)
+    if mobj is not None:
+        numstr = mobj.group(1)
+        if numstr.startswith(u'x'):
+            base = 16
+            numstr = u'0%s' % numstr
+        else:
+            base = 10
+        return compat_chr(int(numstr, base))
+
+    # Unknown entity in name, return its literal representation
+    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):
+    """Modified HTMLParser that isolates a tag with the specified attribute"""
+    def __init__(self, attribute, value):
+        self.attribute = attribute
+        self.value = value
+        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)
+
+    def error(self, message):
+        if self.error_count > 10 or self.started:
+            raise compat_html_parser.HTMLParseError(message, self.getpos())
+        self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
+        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:
+            self.find_startpos(None)
+        if self.attribute in attrs and attrs[self.attribute] == self.value:
+            self.result = [tag]
+            self.started = True
+            self.watch_startpos = True
+        if self.started:
+            if not tag in self.depth: self.depth[tag] = 0
+            self.depth[tag] += 1
+
+    def handle_endtag(self, tag):
+        if self.started:
+            if tag in self.depth: self.depth[tag] -= 1
+            if self.depth[self.result[0]] == 0:
+                self.started = False
+                self.result.append(self.getpos())
+
+    def find_startpos(self, x):
+        """Needed to put the start position of the result (self.result[1])
+        after the opening tag with the requested id"""
+        if self.watch_startpos:
+            self.watch_startpos = False
+            self.result.append(self.getpos())
+    handle_entityref = handle_charref = handle_data = handle_comment = \
+    handle_decl = handle_pi = unknown_decl = find_startpos
+
+    def get_result(self):
+        if self.result is None:
+            return None
+        if len(self.result) != 3:
+            return None
+        lines = self.html.split('\n')
+        lines = lines[self.result[1][0]-1:self.result[2][0]]
+        lines[0] = lines[0][self.result[1][1]:]
+        if len(lines) == 1:
+            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):
 
 def get_element_by_id(id, html):

-       """Return the content of the tag with the specified id in the passed HTML document"""
-       parser = IDParser(id)
-       try:
-               parser.loads(html)
-       except HTMLParser.HTMLParseError:
-               pass
-       return parser.get_result()
+    """Return the content of the tag with the specified ID in the passed HTML document"""
+    return get_element_by_attribute("id", id, html)
+
+def get_element_by_attribute(attribute, value, html):
+    """Return the content of the tag with the specified attribute in the passed HTML document"""
+    parser = AttrParser(attribute, value)
+    try:
+        parser.loads(html)
+    except compat_html_parser.HTMLParseError:
+        pass
+    return parser.get_result()

 
 
 def clean_html(html):
 
 
 def clean_html(html):

-       """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)
-       # Strip html tags
-       html = re.sub('<.*?>', '', html)
-       # Replace html entities
-       html = unescapeHTML(html)
-       return html
+    """Clean an HTML snippet into a readable string"""
+    # Newline vs <br />
+    html = html.replace('\n', ' ')
+    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
+    html = unescapeHTML(html)
+    return html.strip()

 
 
 def sanitize_open(filename, open_mode):
 
 
 def sanitize_open(filename, open_mode):

-       """Try to open the given filename, and slightly tweak it if this fails.
-
-       Attempts to open the given filename. If this fails, it tries to change
-       the filename slightly, step by step, until it's either able to open it
-       or it fails and raises a final exception, like the standard open()
-       function.
-
-       It returns the tuple (stream, definitive_file_name).
-       """
-       try:
-               if filename == u'-':
-                       if sys.platform == 'win32':
-                               import msvcrt
-                               msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
-                       return (sys.stdout, filename)
-               stream = open(encodeFilename(filename), open_mode)
-               return (stream, filename)
-       except (IOError, OSError), err:
-               # In case of error, try to remove win32 forbidden chars
-               filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
-
-               # An exception here should be caught in the caller
-               stream = open(encodeFilename(filename), open_mode)
-               return (stream, filename)
+    """Try to open the given filename, and slightly tweak it if this fails.
+
+    Attempts to open the given filename. If this fails, it tries to change
+    the filename slightly, step by step, until it's either able to open it
+    or it fails and raises a final exception, like the standard open()
+    function.
+
+    It returns the tuple (stream, definitive_file_name).
+    """
+    try:
+        if filename == u'-':
+            if sys.platform == 'win32':
+                import msvcrt
+                msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
+            return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename)
+        stream = open(encodeFilename(filename), open_mode)
+        return (stream, filename)
+    except (IOError, OSError) as err:
+        if err.errno in (errno.EACCES,):
+            raise
+
+        # In case of error, try to remove win32 forbidden chars
+        alt_filename = os.path.join(
+                        re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', path_part)
+                        for path_part in os.path.split(filename)
+                       )
+        if alt_filename == filename:
+            raise
+        else:
+            # An exception here should be caught in the caller
+            stream = open(encodeFilename(filename), open_mode)
+            return (stream, alt_filename)

 
 
 def timeconvert(timestr):
 
 
 def timeconvert(timestr):

-       """Convert RFC 2822 defined time string into system timestamp"""
-       timestamp = None
-       timetuple = email.utils.parsedate_tz(timestr)
-       if timetuple is not None:
-               timestamp = email.utils.mktime_tz(timetuple)
-       return timestamp
-       
-def sanitize_filename(s):
-       """Sanitizes a string so it could be used as part of a filename."""
-       def replace_insane(char):
-               if char in u' .\\/|?*<>:"' or ord(char) < 32:
-                       return '_'
-               return char
-       return u''.join(map(replace_insane, s)).strip('_')
+    """Convert RFC 2822 defined time string into system timestamp"""
+    timestamp = None
+    timetuple = email.utils.parsedate_tz(timestr)
+    if timetuple is not None:
+        timestamp = email.utils.mktime_tz(timetuple)
+    return timestamp
+
+def sanitize_filename(s, restricted=False, is_id=False):
+    """Sanitizes a string so it could be used as part of a filename.
+    If restricted is set, use a stricter subset of allowed characters.
+    Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
+    """
+    def replace_insane(char):
+        if char == '?' or ord(char) < 32 or ord(char) == 127:
+            return ''
+        elif char == '"':
+            return '' if restricted else '\''
+        elif char == ':':
+            return '_-' if restricted else ' -'
+        elif char in '\\/|*<>':
+            return '_'
+        if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
+            return '_'
+        if restricted and ord(char) > 127:
+            return '_'
+        return char
+
+    result = u''.join(map(replace_insane, s))
+    if not is_id:
+        while '__' in result:
+            result = result.replace('__', '_')
+        result = result.strip('_')
+        # Common case of "Foreign band name - English song title"
+        if restricted and result.startswith('-_'):
+            result = result[2:]
+        if not result:
+            result = '_'
+    return result

 
 def orderedSet(iterable):
 
 def orderedSet(iterable):

-       """ Remove all duplicates from the input iterable """
-       res = []
-       for el in iterable:
-               if el not in res:
-                       res.append(el)
-       return res
+    """ Remove all duplicates from the input iterable """
+    res = []
+    for el in iterable:
+        if el not in res:
+            res.append(el)
+    return res

 
 def unescapeHTML(s):
 
 def unescapeHTML(s):

-       """
-       @param s a string (of type unicode)
-       """
-       assert type(s) == type(u'')
+    """
+    @param s a string
+    """
+    assert type(s) == type(u'')

 
 

-       result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s)
-       return result
+    result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s)
+    return result

 
 def encodeFilename(s):
 
 def encodeFilename(s):

-       """
-       @param s The name of the file (of type unicode)
-       """
-
-       assert type(s) == type(u'')
+    """
+    @param s The name of the file
+    """
+
+    assert type(s) == type(u'')
+
+    # Python 3 has a Unicode API
+    if sys.version_info >= (3, 0):
+        return s
+
+    if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
+        # Pass u'' directly to use Unicode APIs on Windows 2000 and up
+        # (Detecting Windows NT 4 is tricky because 'major >= 4' would
+        # match Windows 9x series as well. Besides, NT 4 is obsolete.)
+        return s
+    else:
+        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
+
+def formatSeconds(secs):
+    if secs > 3600:
+        return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
+    elif secs > 60:
+        return '%d:%02d' % (secs // 60, secs % 60)
+    else:
+        return '%d' % secs
+
+def make_HTTPS_handler(opts):
+    if sys.version_info < (3,2):
+        # Python's 2.x handler is very simplistic
+        return compat_urllib_request.HTTPSHandler()
+    else:
+        import ssl
+        context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
+        context.set_default_verify_paths()
+        
+        context.verify_mode = (ssl.CERT_NONE
+                               if opts.no_check_certificate
+                               else ssl.CERT_REQUIRED)
+        return compat_urllib_request.HTTPSHandler(context=context)
+
+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). """
+
+        if not sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
+            msg = msg + u'; please report this issue on http://yt-dl.org/bug'
+        super(ExtractorError, self).__init__(msg)
+
+        self.traceback = tb
+        self.exc_info = sys.exc_info()  # preserve original exception
+
+    def format_traceback(self):
+        if self.traceback is None:
+            return None
+        return u''.join(traceback.format_tb(self.traceback))

 
 

-       if sys.platform == 'win32' and sys.getwindowsversion().major >= 5:
-               # Pass u'' directly to use Unicode APIs on Windows 2000 and up
-               # (Detecting Windows NT 4 is tricky because 'major >= 4' would
-               # match Windows 9x series as well. Besides, NT 4 is obsolete.)
-               return s
-       else:
-               return s.encode(sys.getfilesystemencoding(), 'ignore')

 
 class DownloadError(Exception):
 
 class DownloadError(Exception):

-       """Download Error exception.
+    """Download Error exception.

 
 

-       This exception may be thrown by FileDownloader objects if they are not
-       configured to continue on errors. They will contain the appropriate
-       error message.
-       """
-       pass
+    This exception may be thrown by FileDownloader objects if they are not
+    configured to continue on errors. They will contain the appropriate
+    error message.
+    """
+    def __init__(self, msg, exc_info=None):
+        """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
+        super(DownloadError, self).__init__(msg)
+        self.exc_info = exc_info

 
 
 class SameFileError(Exception):
 
 
 class SameFileError(Exception):

-       """Same File exception.
+    """Same File exception.

 
 

-       This exception will be thrown by FileDownloader objects if they detect
-       multiple files would have to be downloaded to the same file on disk.
-       """
-       pass
+    This exception will be thrown by FileDownloader objects if they detect
+    multiple files would have to be downloaded to the same file on disk.
+    """
+    pass

 
 
 class PostProcessingError(Exception):
 
 
 class PostProcessingError(Exception):

-       """Post Processing exception.
+    """Post Processing exception.

 
 

-       This exception may be raised by PostProcessor's .run() method to
-       indicate an error in the postprocessing task.
-       """
-       pass
+    This exception may be raised by PostProcessor's .run() method to
+    indicate an error in the postprocessing task.
+    """
+    def __init__(self, msg):
+        self.msg = msg

 
 class MaxDownloadsReached(Exception):
 
 class MaxDownloadsReached(Exception):

-       """ --max-downloads limit has been reached. """
-       pass
+    """ --max-downloads limit has been reached. """
+    pass

 
 
 class UnavailableVideoError(Exception):
 
 
 class UnavailableVideoError(Exception):

-       """Unavailable Format exception.
+    """Unavailable Format exception.

 
 

-       This exception will be thrown when a video is requested
-       in a format that is not available for that video.
-       """
-       pass
+    This exception will be thrown when a video is requested
+    in a format that is not available for that video.
+    """
+    pass

 
 
 class ContentTooShortError(Exception):
 
 
 class ContentTooShortError(Exception):

-       """Content Too Short exception.
-
-       This exception may be raised by FileDownloader objects when a file they
-       download is too small for what the server announced first, indicating
-       the connection was probably interrupted.
-       """
-       # Both in bytes
-       downloaded = None
-       expected = None
-
-       def __init__(self, downloaded, 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(urllib2.HTTPHandler):
-       """Handler for HTTP requests and responses.
-
-       This class, when installed with an OpenerDirector, automatically adds
-       the standard headers to every HTTP request and handles gzipped and
-       deflated responses from web servers. If compression is to be avoided in
-       a particular request, the original request in the program code only has
-       to include the HTTP header "Youtubedl-No-Compression", which will be
-       removed before making the real request.
-
-       Part of this code was copied from:
-
-       http://techknack.net/python-urllib2-handlers/
-
-       Andrew Rowls, the author of that code, agreed to release it to the
-       public domain.
-       """
-
-       @staticmethod
-       def deflate(data):
-               try:
-                       return zlib.decompress(data, -zlib.MAX_WBITS)
-               except zlib.error:
-                       return zlib.decompress(data)
-
-       @staticmethod
-       def addinfourl_wrapper(stream, headers, url, code):
-               if hasattr(urllib2.addinfourl, 'getcode'):
-                       return urllib2.addinfourl(stream, headers, url, code)
-               ret = urllib2.addinfourl(stream, headers, url)
-               ret.code = code
-               return ret
-
-       def http_request(self, req):
-               for h in std_headers:
-                       if h in req.headers:
-                               del req.headers[h]
-                       req.add_header(h, std_headers[h])
-               if 'Youtubedl-no-compression' in req.headers:
-                       if 'Accept-encoding' in req.headers:
-                               del req.headers['Accept-encoding']
-                       del req.headers['Youtubedl-no-compression']
-               return req
-
-       def http_response(self, req, resp):
-               old_resp = resp
-               # gzip
-               if resp.headers.get('Content-encoding', '') == 'gzip':
-                       gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
-                       resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
-                       resp.msg = old_resp.msg
-               # deflate
-               if resp.headers.get('Content-encoding', '') == 'deflate':
-                       gz = StringIO.StringIO(self.deflate(resp.read()))
-                       resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
-                       resp.msg = old_resp.msg
-               return resp
+    """Content Too Short exception.
+
+    This exception may be raised by FileDownloader objects when a file they
+    download is too small for what the server announced first, indicating
+    the connection was probably interrupted.
+    """
+    # Both in bytes
+    downloaded = None
+    expected = None
+
+    def __init__(self, downloaded, expected):
+        self.downloaded = downloaded
+        self.expected = expected
+
+class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
+    """Handler for HTTP requests and responses.
+
+    This class, when installed with an OpenerDirector, automatically adds
+    the standard headers to every HTTP request and handles gzipped and
+    deflated responses from web servers. If compression is to be avoided in
+    a particular request, the original request in the program code only has
+    to include the HTTP header "Youtubedl-No-Compression", which will be
+    removed before making the real request.
+
+    Part of this code was copied from:
+
+    http://techknack.net/python-urllib2-handlers/
+
+    Andrew Rowls, the author of that code, agreed to release it to the
+    public domain.
+    """
+
+    @staticmethod
+    def deflate(data):
+        try:
+            return zlib.decompress(data, -zlib.MAX_WBITS)
+        except zlib.error:
+            return zlib.decompress(data)
+
+    @staticmethod
+    def addinfourl_wrapper(stream, headers, url, code):
+        if hasattr(compat_urllib_request.addinfourl, 'getcode'):
+            return compat_urllib_request.addinfourl(stream, headers, url, code)
+        ret = compat_urllib_request.addinfourl(stream, headers, url)
+        ret.code = code
+        return ret
+
+    def http_request(self, req):
+        for h,v in std_headers.items():
+            if h in req.headers:
+                del req.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-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):
+        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)
+            resp.msg = old_resp.msg
+        # deflate
+        if resp.headers.get('Content-encoding', '') == 'deflate':
+            gz = io.BytesIO(self.deflate(resp.read()))
+            resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+            resp.msg = old_resp.msg
+        return resp
+
+    https_request = http_request
+    https_response = http_response
+
+def unified_strdate(date_str):
+    """Return a string with the date in the format YYYYMMDD"""
+    upload_date = None
+    #Replace commas
+    date_str = date_str.replace(',',' ')
+    # %z (UTC offset) is only supported in python>=3.2
+    date_str = re.sub(r' (\+|-)[\d]*$', '', date_str)
+    format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S']
+    for expression in format_expressions:
+        try:
+            upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
+        except:
+            pass
+    return upload_date
+
+def date_from_str(date_str):
+    """
+    Return a datetime object from a string in the format YYYYMMDD or
+    (now|today)[+-][0-9](day|week|month|year)(s)?"""
+    today = datetime.date.today()
+    if date_str == 'now'or date_str == 'today':
+        return today
+    match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
+    if match is not None:
+        sign = match.group('sign')
+        time = int(match.group('time'))
+        if sign == '-':
+            time = -time
+        unit = match.group('unit')
+        #A bad aproximation?
+        if unit == 'month':
+            unit = 'day'
+            time *= 30
+        elif unit == 'year':
+            unit = 'day'
+            time *= 365
+        unit += 's'
+        delta = datetime.timedelta(**{unit: time})
+        return today + delta
+    return datetime.datetime.strptime(date_str, "%Y%m%d").date()
+    
+class DateRange(object):
+    """Represents a time interval between two dates"""
+    def __init__(self, start=None, end=None):
+        """start and end must be strings in the format accepted by date"""
+        if start is not None:
+            self.start = date_from_str(start)
+        else:
+            self.start = datetime.datetime.min.date()
+        if end is not None:
+            self.end = date_from_str(end)
+        else:
+            self.end = datetime.datetime.max.date()
+        if self.start > self.end:
+            raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
+    @classmethod
+    def day(cls, day):
+        """Returns a range that only contains the given day"""
+        return cls(day,day)
+    def __contains__(self, date):
+        """Check if the date is in the range"""
+        if not isinstance(date, datetime.date):
+            date = date_from_str(date)
+        return self.start <= date <= self.end
+    def __str__(self):
+        return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())