# -*- coding: utf-8 -*-
import gzip
-import htmlentitydefs
-import HTMLParser
+import io
import locale
import os
import re
import sys
import zlib
-import urllib2
import email.utils
+import json
try:
- import cStringIO as StringIO
-except ImportError:
- import StringIO
-
+ 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:
+ 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 urllib.parse import parse_qs as compat_parse_qs
+except ImportError: # Python 2
+ from urlparse import parse_qs as compat_parse_qs
+
try:
- import json
-except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
- import trivialjson as json
+ compat_str = unicode # Python 2
+except NameError:
+ compat_str = str
+
+try:
+ compat_chr = unichr # Python 2
+except NameError:
+ compat_chr = chr
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
+ '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():
"""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()
+ 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)
def htmlentity_transform(matchobj):
- """Transforms an HTML entity to a Unicode character.
+ """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 htmlentitydefs.name2codepoint:
- return unichr(htmlentitydefs.name2codepoint[entity])
+ if entity in compat_html_entities.name2codepoint:
+ return compat_chr(compat_html_entities.name2codepoint[entity])
- # Unicode character
- mobj = re.match(ur'(?u)#(x?\d+)', entity)
+ mobj = re.match(u'(?u)#(x?\\d+)', entity)
if mobj is not None:
numstr = mobj.group(1)
if numstr.startswith(u'x'):
numstr = u'0%s' % numstr
else:
base = 10
- return unichr(long(numstr, base))
+ 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 IDParser(compat_html_parser.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
+ 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 '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 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()
+
+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 compat_html_parser.HTMLParseError:
+ pass
+ return parser.get_result()
+
-def sanitize_title(utitle):
- """Sanitizes a video title so it could be used as part of a filename."""
- utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
- return utitle.replace(unicode(os.sep), u'%')
+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
def sanitize_open(filename, open_mode):
return (sys.stdout, filename)
stream = open(encodeFilename(filename), open_mode)
return (stream, filename)
- except (IOError, OSError), err:
+ except (IOError, OSError) as err:
# In case of error, try to remove win32 forbidden chars
- filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
+ filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename)
# An exception here should be caught in the caller
stream = open(encodeFilename(filename), open_mode)
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
-def simplify_title(title):
- expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
- return expr.sub(u'_', title).strip(u'_')
+def sanitize_filename(s, restricted=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.
+ """
+ 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))
+ 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):
""" Remove all duplicates from the input iterable """
def unescapeHTML(s):
"""
- @param s a string (of type unicode)
+ @param s a string
"""
assert type(s) == type(u'')
- htmlParser = HTMLParser.HTMLParser()
- return htmlParser.unescape(s)
+ result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s)
+ return result
def encodeFilename(s):
"""
- @param s The name of the file (of type unicode)
+ @param s The name of the file
"""
assert type(s) == type(u'')
- if sys.platform == 'win32' and sys.getwindowsversion().major >= 5:
+ # 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.)
self.expected = expected
-class YoutubeDLHandler(urllib2.HTTPHandler):
+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.
This class, when installed with an OpenerDirector, automatically adds
@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)
+ 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
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
- gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
+ 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 = StringIO.StringIO(self.deflate(resp.read()))
+ 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