Browse Source

delete 'modules' folder

master
imDMG 3 years ago committed by GitHub
parent
commit
ecfd5c8473
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
  1. 123
      modules/helpers.py
  2. 190
      modules/nova2.py
  3. 63
      modules/nova2dl.py
  4. 67
      modules/novaprinter.py
  5. 547
      modules/sgmllib3.py
  6. 391
      modules/socks.py

123
modules/helpers.py

@ -1,123 +0,0 @@ @@ -1,123 +0,0 @@
#VERSION: 1.43
# Author:
# Christophe DUMEZ (chris@qbittorrent.org)
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of the author nor the names of its contributors may be
# used to endorse or promote products derived from this software without
# specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
import gzip
import html.entities
import io
import os
import re
import socket
import socks
import tempfile
import urllib.error
import urllib.parse
import urllib.request
# Some sites blocks default python User-agent
user_agent = 'Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101 Firefox/68.0'
headers = {'User-Agent': user_agent}
# SOCKS5 Proxy support
if "sock_proxy" in os.environ and len(os.environ["sock_proxy"].strip()) > 0:
proxy_str = os.environ["sock_proxy"].strip()
m = re.match(r"^(?:(?P<username>[^:]+):(?P<password>[^@]+)@)?(?P<host>[^:]+):(?P<port>\w+)$",
proxy_str)
if m is not None:
socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, m.group('host'),
int(m.group('port')), True, m.group('username'), m.group('password'))
socket.socket = socks.socksocket
def htmlentitydecode(s):
# First convert alpha entities (such as &eacute;)
# (Inspired from http://mail.python.org/pipermail/python-list/2007-June/443813.html)
def entity2char(m):
entity = m.group(1)
if entity in html.entities.name2codepoint:
return chr(html.entities.name2codepoint[entity])
return " " # Unknown entity: We replace with a space.
t = re.sub('&(%s);' % '|'.join(html.entities.name2codepoint), entity2char, s)
# Then convert numerical entities (such as &#233;)
t = re.sub(r'&#(\d+);', lambda x: chr(int(x.group(1))), t)
# Then convert hexa entities (such as &#x00E9;)
return re.sub(r'&#x(\w+);', lambda x: chr(int(x.group(1), 16)), t)
def retrieve_url(url):
""" Return the content of the url page as a string """
req = urllib.request.Request(url, headers=headers)
try:
response = urllib.request.urlopen(req)
except urllib.error.URLError as errno:
print(" ".join(("Connection error:", str(errno.reason))))
return ""
dat = response.read()
# Check if it is gzipped
if dat[:2] == b'\x1f\x8b':
# Data is gzip encoded, decode it
compressedstream = io.BytesIO(dat)
gzipper = gzip.GzipFile(fileobj=compressedstream)
extracted_data = gzipper.read()
dat = extracted_data
info = response.info()
charset = 'utf-8'
try:
ignore, charset = info['Content-Type'].split('charset=')
except Exception:
pass
dat = dat.decode(charset, 'replace')
dat = htmlentitydecode(dat)
# return dat.encode('utf-8', 'replace')
return dat
def download_file(url, referer=None):
""" Download file at url and write it to a file, return the path to the file and the url """
file, path = tempfile.mkstemp()
file = os.fdopen(file, "wb")
# Download url
req = urllib.request.Request(url, headers=headers)
if referer is not None:
req.add_header('referer', referer)
response = urllib.request.urlopen(req)
dat = response.read()
# Check if it is gzipped
if dat[:2] == b'\x1f\x8b':
# Data is gzip encoded, decode it
compressedstream = io.BytesIO(dat)
gzipper = gzip.GzipFile(fileobj=compressedstream)
extracted_data = gzipper.read()
dat = extracted_data
# Write it to a file
file.write(dat)
file.close()
# return file path
return (path + " " + url)

190
modules/nova2.py

@ -1,190 +0,0 @@ @@ -1,190 +0,0 @@
#VERSION: 1.43
# Author:
# Fabien Devaux <fab AT gnux DOT info>
# Contributors:
# Christophe Dumez <chris@qbittorrent.org> (qbittorrent integration)
# Thanks to gab #gcu @ irc.freenode.net (multipage support on PirateBay)
# Thanks to Elias <gekko04@users.sourceforge.net> (torrentreactor and isohunt search engines)
#
# Licence: BSD
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of the author nor the names of its contributors may be
# used to endorse or promote products derived from this software without
# specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
import urllib.parse
from os import path
from glob import glob
from sys import argv
from multiprocessing import Pool, cpu_count
THREADED = True
try:
MAX_THREADS = cpu_count()
except NotImplementedError:
MAX_THREADS = 1
CATEGORIES = {'all', 'movies', 'tv', 'music', 'games', 'anime', 'software', 'pictures', 'books'}
################################################################################
# Every engine should have a "search" method taking
# a space-free string as parameter (ex. "family+guy")
# it should call prettyPrinter() with a dict as parameter.
# The keys in the dict must be: link,name,size,seeds,leech,engine_url
# As a convention, try to list results by decreasing number of seeds or similar
################################################################################
def initialize_engines():
""" Import available engines
Return list of available engines
"""
supported_engines = []
engines = glob(path.join(path.dirname(__file__), 'engines', '*.py'))
for engine in engines:
engi = path.basename(engine).split('.')[0].strip()
if len(engi) == 0 or engi.startswith('_'):
continue
try:
# import engines.[engine]
engine_module = __import__(".".join(("engines", engi)))
# get low-level module
engine_module = getattr(engine_module, engi)
# bind class name
globals()[engi] = getattr(engine_module, engi)
supported_engines.append(engi)
except Exception:
pass
return supported_engines
def engines_to_xml(supported_engines):
""" Generates xml for supported engines """
tab = " " * 4
for short_name in supported_engines:
search_engine = globals()[short_name]()
supported_categories = ""
if hasattr(search_engine, "supported_categories"):
supported_categories = " ".join((key
for key in search_engine.supported_categories.keys()
if key != "all"))
yield "".join((tab, "<", short_name, ">\n",
tab, tab, "<name>", search_engine.name, "</name>\n",
tab, tab, "<url>", search_engine.url, "</url>\n",
tab, tab, "<categories>", supported_categories, "</categories>\n",
tab, "</", short_name, ">\n"))
def displayCapabilities(supported_engines):
"""
Display capabilities in XML format
<capabilities>
<engine_short_name>
<name>long name</name>
<url>http://example.com</url>
<categories>movies music games</categories>
</engine_short_name>
</capabilities>
"""
xml = "".join(("<capabilities>\n",
"".join(engines_to_xml(supported_engines)),
"</capabilities>"))
print(xml)
def run_search(engine_list):
""" Run search in engine
@param engine_list List with engine, query and category
@retval False if any exceptions occurred
@retval True otherwise
"""
engine, what, cat = engine_list
try:
engine = engine()
# avoid exceptions due to invalid category
if hasattr(engine, 'supported_categories'):
if cat in engine.supported_categories:
engine.search(what, cat)
else:
engine.search(what)
return True
except Exception:
return False
def main(args):
supported_engines = initialize_engines()
if not args:
raise SystemExit("./nova2.py [all|engine1[,engine2]*] <category> <keywords>\n"
"available engines: %s" % (','.join(supported_engines)))
elif args[0] == "--capabilities":
displayCapabilities(supported_engines)
return
elif len(args) < 3:
raise SystemExit("./nova2.py [all|engine1[,engine2]*] <category> <keywords>\n"
"available engines: %s" % (','.join(supported_engines)))
# get only unique engines with set
engines_list = set(e.lower() for e in args[0].strip().split(','))
if 'all' in engines_list:
engines_list = supported_engines
else:
# discard un-supported engines
engines_list = [engine for engine in engines_list
if engine in supported_engines]
if not engines_list:
# engine list is empty. Nothing to do here
return
cat = args[1].lower()
if cat not in CATEGORIES:
raise SystemExit(" - ".join(('Invalid category', cat)))
what = urllib.parse.quote(' '.join(args[2:]))
if THREADED:
# child process spawning is controlled min(number of searches, number of cpu)
with Pool(min(len(engines_list), MAX_THREADS)) as pool:
pool.map(run_search, ([globals()[engine], what, cat] for engine in engines_list))
else:
# py3 note: map is needed to be evaluated for content to be executed
all(map(run_search, ([globals()[engine], what, cat] for engine in engines_list)))
if __name__ == "__main__":
main(argv[1:])

63
modules/nova2dl.py

@ -1,63 +0,0 @@ @@ -1,63 +0,0 @@
#VERSION: 1.22
# Author:
# Christophe DUMEZ (chris@qbittorrent.org)
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of the author nor the names of its contributors may be
# used to endorse or promote products derived from this software without
# specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
import sys
import os
import glob
from helpers import download_file
supported_engines = dict()
engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines', '*.py'))
for engine in engines:
e = engine.split(os.sep)[-1][:-3]
if len(e.strip()) == 0:
continue
if e.startswith('_'):
continue
try:
exec("from engines.%s import %s" % (e, e))
exec("engine_url = %s.url" % e)
supported_engines[engine_url] = e
except Exception:
pass
if __name__ == '__main__':
if len(sys.argv) < 3:
raise SystemExit('./nova2dl.py engine_url download_parameter')
engine_url = sys.argv[1].strip()
download_param = sys.argv[2].strip()
if engine_url not in list(supported_engines.keys()):
raise SystemExit('./nova2dl.py: this engine_url was not recognized')
exec("engine = %s()" % supported_engines[engine_url])
if hasattr(engine, 'download_torrent'):
engine.download_torrent(download_param)
else:
print(download_file(download_param))
sys.exit(0)

67
modules/novaprinter.py

@ -1,67 +0,0 @@ @@ -1,67 +0,0 @@
#VERSION: 1.46
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of the author nor the names of its contributors may be
# used to endorse or promote products derived from this software without
# specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
def prettyPrinter(dictionary):
dictionary['size'] = anySizeToBytes(dictionary['size'])
outtext = "|".join((dictionary["link"], dictionary["name"].replace("|", " "),
str(dictionary["size"]), str(dictionary["seeds"]),
str(dictionary["leech"]), dictionary["engine_url"]))
if 'desc_link' in dictionary:
outtext = "|".join((outtext, dictionary["desc_link"]))
# fd 1 is stdout
with open(1, 'w', encoding='utf-8', closefd=False) as utf8stdout:
print(outtext, file=utf8stdout)
def anySizeToBytes(size_string):
"""
Convert a string like '1 KB' to '1024' (bytes)
"""
# separate integer from unit
try:
size, unit = size_string.split()
except:
try:
size = size_string.strip()
unit = ''.join([c for c in size if c.isalpha()])
if len(unit) > 0:
size = size[:-len(unit)]
except:
return -1
if len(size) == 0:
return -1
size = float(size)
if len(unit) == 0:
return int(size)
short_unit = unit.upper()[0]
# convert
units_dict = {'T': 40, 'G': 30, 'M': 20, 'K': 10}
if short_unit in units_dict:
size = size * 2**units_dict[short_unit]
return int(size)

547
modules/sgmllib3.py

@ -1,547 +0,0 @@ @@ -1,547 +0,0 @@
"""A parser for SGML, using the derived class as a static DTD."""
# XXX This only supports those SGML features used by HTML.
# XXX There should be a way to distinguish between PCDATA (parsed
# character data -- the normal case), RCDATA (replaceable character
# data -- only char and entity references and end tags are special)
# and CDATA (character data -- only end tags are special). RCDATA is
# not supported at all.
import _markupbase
import re
__all__ = ["SGMLParser", "SGMLParseError"]
# Regular expressions used for parsing
interesting = re.compile('[&<]')
incomplete = re.compile('&([a-zA-Z][a-zA-Z0-9]*|#[0-9]*)?|'
'<([a-zA-Z][^<>]*|'
'/([a-zA-Z][^<>]*)?|'
'![^<>]*)?')
entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
charref = re.compile('&#([0-9]+)[^0-9]')
starttagopen = re.compile('<[>a-zA-Z]')
shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/')
shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/')
piclose = re.compile('>')
endbracket = re.compile('[<>]')
tagfind = re.compile('[a-zA-Z][-_.a-zA-Z0-9]*')
attrfind = re.compile(
r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*'
r'(\'[^\']*\'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*))?')
class SGMLParseError(RuntimeError):
"""Exception raised for all parse errors."""
pass
# SGML parser base class -- find tags and call handler functions.
# Usage: p = SGMLParser(); p.feed(data); ...; p.close().
# The dtd is defined by deriving a class which defines methods
# with special names to handle tags: start_foo and end_foo to handle
# <foo> and </foo>, respectively, or do_foo to handle <foo> by itself.
# (Tags are converted to lower case for this purpose.) The data
# between tags is passed to the parser by calling self.handle_data()
# with some data as argument (the data may be split up in arbitrary
# chunks). Entity references are passed by calling
# self.handle_entityref() with the entity reference as argument.
class SGMLParser(_markupbase.ParserBase):
# Definition of entities -- derived classes may override
entity_or_charref = re.compile('&(?:'
'([a-zA-Z][-.a-zA-Z0-9]*)|#([0-9]+)'
')(;?)')
def __init__(self, verbose=0):
"""Initialize and reset this instance."""
self.verbose = verbose
self.reset()
def reset(self):
"""Reset this instance. Loses all unprocessed data."""
self.__starttag_text = None
self.rawdata = ''
self.stack = []
self.lasttag = '???'
self.nomoretags = 0
self.literal = 0
_markupbase.ParserBase.reset(self)
def setnomoretags(self):
"""Enter literal mode (CDATA) till EOF.
Intended for derived classes only.
"""
self.nomoretags = self.literal = 1
def setliteral(self, *args):
"""Enter literal mode (CDATA).
Intended for derived classes only.
"""
self.literal = 1
def feed(self, data):
"""Feed some data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n'). (This just saves the text,
all the processing is done by goahead().)
"""
self.rawdata = self.rawdata + data
self.goahead(0)
def close(self):
"""Handle the remaining data."""
self.goahead(1)
def error(self, message):
raise SGMLParseError(message)
# Internal -- handle data as far as reasonable. May leave state
# and data to be processed by a subsequent call. If 'end' is
# true, force handling all data as if followed by EOF marker.
def goahead(self, end):
rawdata = self.rawdata
i = 0
n = len(rawdata)
while i < n:
if self.nomoretags:
self.handle_data(rawdata[i:n])
i = n
break
match = interesting.search(rawdata, i)
if match: j = match.start()
else: j = n
if i < j:
self.handle_data(rawdata[i:j])
i = j
if i == n: break
if rawdata[i] == '<':
if starttagopen.match(rawdata, i):
if self.literal:
self.handle_data(rawdata[i])
i = i+1
continue
k = self.parse_starttag(i)
if k < 0: break
i = k
continue
if rawdata.startswith("</", i):
k = self.parse_endtag(i)
if k < 0: break
i = k
self.literal = 0
continue
if self.literal:
if n > (i + 1):
self.handle_data("<")
i = i+1
else:
# incomplete
break
continue
if rawdata.startswith("<!--", i):
# Strictly speaking, a comment is --.*--
# within a declaration tag <!...>.
# This should be removed,
# and comments handled only in parse_declaration.
k = self.parse_comment(i)
if k < 0: break
i = k
continue
if rawdata.startswith("<?", i):
k = self.parse_pi(i)
if k < 0: break
i = i+k
continue
if rawdata.startswith("<!", i):
# This is some sort of declaration; in "HTML as
# deployed," this should only be the document type
# declaration ("<!DOCTYPE html...>").
k = self.parse_declaration(i)
if k < 0: break
i = k
continue
elif rawdata[i] == '&':
if self.literal:
self.handle_data(rawdata[i])
i = i+1
continue
match = charref.match(rawdata, i)
if match:
name = match.group(1)
self.handle_charref(name)
i = match.end(0)
if rawdata[i-1] != ';': i = i-1
continue
match = entityref.match(rawdata, i)
if match:
name = match.group(1)
self.handle_entityref(name)
i = match.end(0)
if rawdata[i-1] != ';': i = i-1
continue
else:
self.error('neither < nor & ??')
# We get here only if incomplete matches but
# nothing else
match = incomplete.match(rawdata, i)
if not match:
self.handle_data(rawdata[i])
i = i+1
continue
j = match.end(0)
if j == n:
break # Really incomplete
self.handle_data(rawdata[i:j])
i = j
# end while
if end and i < n:
self.handle_data(rawdata[i:n])
i = n
self.rawdata = rawdata[i:]
# XXX if end: check for empty stack
# Extensions for the DOCTYPE scanner:
_decl_otherchars = '='
# Internal -- parse processing instr, return length or -1 if not terminated
def parse_pi(self, i):
rawdata = self.rawdata
if rawdata[i:i+2] != '<?':
self.error('unexpected call to parse_pi()')
match = piclose.search(rawdata, i+2)
if not match:
return -1
j = match.start(0)
self.handle_pi(rawdata[i+2: j])
j = match.end(0)
return j-i
def get_starttag_text(self):
return self.__starttag_text
# Internal -- handle starttag, return length or -1 if not terminated
def parse_starttag(self, i):
self.__starttag_text = None
start_pos = i
rawdata = self.rawdata
if shorttagopen.match(rawdata, i):
# SGML shorthand: <tag/data/ == <tag>data</tag>
# XXX Can data contain &... (entity or char refs)?
# XXX Can data contain < or > (tag characters)?
# XXX Can there be whitespace before the first /?
match = shorttag.match(rawdata, i)
if not match:
return -1
tag, data = match.group(1, 2)
self.__starttag_text = '<%s/' % tag
tag = tag.lower()
k = match.end(0)
self.finish_shorttag(tag, data)
self.__starttag_text = rawdata[start_pos:match.end(1) + 1]
return k
# XXX The following should skip matching quotes (' or ")
# As a shortcut way to exit, this isn't so bad, but shouldn't
# be used to locate the actual end of the start tag since the
# < or > characters may be embedded in an attribute value.
match = endbracket.search(rawdata, i+1)
if not match:
return -1
j = match.start(0)
# Now parse the data between i+1 and j into a tag and attrs
attrs = []
if rawdata[i:i+2] == '<>':
# SGML shorthand: <> == <last open tag seen>
k = j
tag = self.lasttag
else:
match = tagfind.match(rawdata, i+1)
if not match:
self.error('unexpected call to parse_starttag')
k = match.end(0)
tag = rawdata[i+1:k].lower()
self.lasttag = tag
while k < j:
match = attrfind.match(rawdata, k)
if not match: break
attrname, rest, attrvalue = match.group(1, 2, 3)
if not rest:
attrvalue = attrname
else:
if (attrvalue[:1] == "'" == attrvalue[-1:] or
attrvalue[:1] == '"' == attrvalue[-1:]):
# strip quotes
attrvalue = attrvalue[1:-1]
attrvalue = self.entity_or_charref.sub(
self._convert_ref, attrvalue)
attrs.append((attrname.lower(), attrvalue))
k = match.end(0)
if rawdata[j] == '>':
j = j+1
self.__starttag_text = rawdata[start_pos:j]
self.finish_starttag(tag, attrs)
return j
# Internal -- convert entity or character reference
def _convert_ref(self, match):
if match.group(2):
return self.convert_charref(match.group(2)) or \
'&#%s%s' % match.groups()[1:]
elif match.group(3):
return self.convert_entityref(match.group(1)) or \
'&%s;' % match.group(1)
else:
return '&%s' % match.group(1)
# Internal -- parse endtag
def parse_endtag(self, i):
rawdata = self.rawdata
match = endbracket.search(rawdata, i+1)
if not match:
return -1
j = match.start(0)
tag = rawdata[i+2:j].strip().lower()
if rawdata[j] == '>':
j = j+1
self.finish_endtag(tag)
return j
# Internal -- finish parsing of <tag/data/ (same as <tag>data</tag>)
def finish_shorttag(self, tag, data):
self.finish_starttag(tag, [])
self.handle_data(data)
self.finish_endtag(tag)
# Internal -- finish processing of start tag
# Return -1 for unknown tag, 0 for open-only tag, 1 for balanced tag
def finish_starttag(self, tag, attrs):
try:
method = getattr(self, 'start_' + tag)
except AttributeError:
try:
method = getattr(self, 'do_' + tag)
except AttributeError:
self.unknown_starttag(tag, attrs)
return -1
else:
self.handle_starttag(tag, method, attrs)
return 0
else:
self.stack.append(tag)
self.handle_starttag(tag, method, attrs)
return 1
# Internal -- finish processing of end tag
def finish_endtag(self, tag):
if not tag:
found = len(self.stack) - 1
if found < 0:
self.unknown_endtag(tag)
return
else:
if tag not in self.stack:
try:
method = getattr(self, 'end_' + tag)
except AttributeError:
self.unknown_endtag(tag)
else:
self.report_unbalanced(tag)
return
found = len(self.stack)
for i in range(found):
if self.stack[i] == tag: found = i
while len(self.stack) > found:
tag = self.stack[-1]
try:
method = getattr(self, 'end_' + tag)
except AttributeError:
method = None
if method:
self.handle_endtag(tag, method)
else:
self.unknown_endtag(tag)
del self.stack[-1]
# Overridable -- handle start tag
def handle_starttag(self, tag, method, attrs):
method(attrs)
# Overridable -- handle end tag
def handle_endtag(self, tag, method):
method()
# Example -- report an unbalanced </...> tag.
def report_unbalanced(self, tag):
if self.verbose:
print('*** Unbalanced </' + tag + '>')
print('*** Stack:', self.stack)
def convert_charref(self, name):
"""Convert character reference, may be overridden."""
try:
n = int(name)
except ValueError:
return
if not 0 <= n <= 127:
return
return self.convert_codepoint(n)
def convert_codepoint(self, codepoint):
return chr(codepoint)
def handle_charref(self, name):
"""Handle character reference, no need to override."""
replacement = self.convert_charref(name)
if replacement is None:
self.unknown_charref(name)
else:
self.handle_data(replacement)
# Definition of entities -- derived classes may override
entitydefs = \
{'lt': '<', 'gt': '>', 'amp': '&', 'quot': '"', 'apos': '\''}
def convert_entityref(self, name):
"""Convert entity references.
As an alternative to overriding this method; one can tailor the
results by setting up the self.entitydefs mapping appropriately.
"""
table = self.entitydefs
if name in table:
return table[name]
else:
return
def handle_entityref(self, name):
"""Handle entity references, no need to override."""
replacement = self.convert_entityref(name)
if replacement is None:
self.unknown_entityref(name)
else:
self.handle_data(replacement)
# Example -- handle data, should be overridden
def handle_data(self, data):
pass
# Example -- handle comment, could be overridden
def handle_comment(self, data):
pass
# Example -- handle declaration, could be overridden
def handle_decl(self, decl):
pass
# Example -- handle processing instruction, could be overridden
def handle_pi(self, data):
pass
# To be overridden -- handlers for unknown objects
def unknown_starttag(self, tag, attrs): pass
def unknown_endtag(self, tag): pass
def unknown_charref(self, ref): pass
def unknown_entityref(self, ref): pass
class TestSGMLParser(SGMLParser):
def __init__(self, verbose=0):
self.testdata = ""
SGMLParser.__init__(self, verbose)
def handle_data(self, data):
self.testdata = self.testdata + data
if len(repr(self.testdata)) >= 70:
self.flush()
def flush(self):
data = self.testdata
if data:
self.testdata = ""
print('data:', repr(data))
def handle_comment(self, data):
self.flush()
r = repr(data)
if len(r) > 68:
r = r[:32] + '...' + r[-32:]
print('comment:', r)
def unknown_starttag(self, tag, attrs):
self.flush()
if not attrs:
print('start tag: <' + tag + '>')
else:
print('start tag: <' + tag, end=' ')
for name, value in attrs:
print(name + '=' + '"' + value + '"', end=' ')
print('>')
def unknown_endtag(self, tag):
self.flush()
print('end tag: </' + tag + '>')
def unknown_entityref(self, ref):
self.flush()
print('*** unknown entity ref: &' + ref + ';')
def unknown_charref(self, ref):
self.flush()
print('*** unknown char ref: &#' + ref + ';')
def unknown_decl(self, data):
self.flush()
print('*** unknown decl: [' + data + ']')
def close(self):
SGMLParser.close(self)
self.flush()
def test(args = None):
import sys
if args is None:
args = sys.argv[1:]
if args and args[0] == '-s':
args = args[1:]
klass = SGMLParser
else:
klass = TestSGMLParser
if args:
file = args[0]
else:
file = 'test.html'
if file == '-':
f = sys.stdin
else:
try:
f = open(file, 'r')
except IOError as msg:
print(file, ":", msg)
sys.exit(1)
data = f.read()
if f is not sys.stdin:
f.close()
x = klass()
for c in data:
x.feed(c)
x.close()
if __name__ == '__main__':
test()

391
modules/socks.py

@ -1,391 +0,0 @@ @@ -1,391 +0,0 @@
"""SocksiPy - Python SOCKS module.
Version 1.01
Copyright 2006 Dan-Haim. All rights reserved.
Various fixes by Christophe DUMEZ <chris@qbittorrent.org> - 2010
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3. Neither the name of Dan Haim nor the names of his contributors may be used
to endorse or promote products derived from this software without specific
prior written permission.
THIS SOFTWARE IS PROVIDED BY DAN HAIM "AS IS" AND ANY EXPRESS OR IMPLIED
WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
EVENT SHALL DAN HAIM OR HIS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA
OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMANGE.
This module provides a standard socket-like interface for Python
for tunneling connections through SOCKS proxies.
"""
import socket
import struct
PROXY_TYPE_SOCKS4 = 1
PROXY_TYPE_SOCKS5 = 2
PROXY_TYPE_HTTP = 3
_defaultproxy = None
_orgsocket = socket.socket
class ProxyError(Exception):
def __init__(self, value):
self.value = value
def __str__(self):
return repr(self.value)
class GeneralProxyError(ProxyError):
def __init__(self, value):
self.value = value
def __str__(self):
return repr(self.value)
class Socks5AuthError(ProxyError):
def __init__(self, value):
self.value = value
def __str__(self):
return repr(self.value)
class Socks5Error(ProxyError):
def __init__(self, value):
self.value = value
def __str__(self):
return repr(self.value)
class Socks4Error(ProxyError):
def __init__(self, value):
self.value = value
def __str__(self):
return repr(self.value)
class HTTPError(ProxyError):
def __init__(self, value):
self.value = value
def __str__(self):
return repr(self.value)
_generalerrors = ("success",
"invalid data",
"not connected",
"not available",
"bad proxy type",
"bad input")
_socks5errors = ("succeeded",
"general SOCKS server failure",
"connection not allowed by ruleset",
"Network unreachable",
"Host unreachable",
"Connection refused",
"TTL expired",
"Command not supported",
"Address type not supported",
"Unknown error")
_socks5autherrors = ("succeeded",
"authentication is required",
"all offered authentication methods were rejected",
"unknown username or invalid password",
"unknown error")
_socks4errors = ("request granted",
"request rejected or failed",
"request rejected because SOCKS server cannot connect to identd on the client",
"request rejected because the client program and identd report different user-ids",
"unknown error")
def setdefaultproxy(proxytype=None,addr=None,port=None,rdns=True,username=None,password=None):
"""setdefaultproxy(proxytype, addr[, port[, rdns[, username[, password]]]])
Sets a default proxy which all further socksocket objects will use,
unless explicitly changed.
"""
global _defaultproxy
_defaultproxy = (proxytype,addr,port,rdns,username,password)
class socksocket(socket.socket):
"""socksocket([family[, type[, proto]]]) -> socket object
Open a SOCKS enabled socket. The parameters are the same as
those of the standard socket init. In order for SOCKS to work,
you must specify family=AF_INET, type=SOCK_STREAM and proto=0.
"""
def __init__(self, family=socket.AF_INET, type=socket.SOCK_STREAM, proto=0, _sock=None):
_orgsocket.__init__(self,family,type,proto,_sock)
if _defaultproxy != None:
self.__proxy = _defaultproxy
else:
self.__proxy = (None, None, None, None, None, None)
self.__proxysockname = None
self.__proxypeername = None
def __recvall(self, bytes):
"""__recvall(bytes) -> data
Receive EXACTLY the number of bytes requested from the socket.
Blocks until the required number of bytes have been received.
"""
data = ""
while len(data) < bytes:
d = self.recv(bytes-len(data))
if not d:
raise GeneralProxyError("connection closed unexpectedly")
data = data + d
return data
def setproxy(self,proxytype=None,addr=None,port=None,rdns=True,username=None,password=None):
"""setproxy(proxytype, addr[, port[, rdns[, username[, password]]]])
Sets the proxy to be used.
proxytype - The type of the proxy to be used. Three types
are supported: PROXY_TYPE_SOCKS4 (including socks4a),
PROXY_TYPE_SOCKS5 and PROXY_TYPE_HTTP
addr - The address of the server (IP or DNS).
port - The port of the server. Defaults to 1080 for SOCKS
servers and 8080 for HTTP proxy servers.
rdns - Should DNS queries be preformed on the remote side
(rather than the local side). The default is True.
Note: This has no effect with SOCKS4 servers.
username - Username to authenticate with to the server.
The default is no authentication.
password - Password to authenticate with to the server.
Only relevant when username is also provided.
"""
self.__proxy = (proxytype,addr,port,rdns,username,password)
def __negotiatesocks5(self,destaddr,destport):
"""__negotiatesocks5(self,destaddr,destport)
Negotiates a connection through a SOCKS5 server.
"""
# First we'll send the authentication packages we support.
if (self.__proxy[4]!=None) and (self.__proxy[5]!=None):
# The username/password details were supplied to the
# setproxy method so we support the USERNAME/PASSWORD
# authentication (in addition to the standard none).
self.sendall("\x05\x02\x00\x02")
else:
# No username/password were entered, therefore we
# only support connections with no authentication.
self.sendall("\x05\x01\x00")
# We'll receive the server's response to determine which
# method was selected
chosenauth = self.__recvall(2)
if chosenauth[0] != "\x05":
self.close()
raise GeneralProxyError((1,_generalerrors[1]))
# Check the chosen authentication method
if chosenauth[1] == "\x00":
# No authentication is required
pass
elif chosenauth[1] == "\x02":
# Okay, we need to perform a basic username/password
# authentication.
self.sendall("\x01" + chr(len(self.__proxy[4])) + self.__proxy[4] + chr(len(self.__proxy[5])) + self.__proxy[5])
authstat = self.__recvall(2)
if authstat[0] != "\x01":
# Bad response
self.close()
raise GeneralProxyError((1,_generalerrors[1]))
if authstat[1] != "\x00":
# Authentication failed
self.close()
raise Socks5AuthError((3,_socks5autherrors[3]))
# Authentication succeeded
else:
# Reaching here is always bad
self.close()
if chosenauth[1] == "\xFF":
raise Socks5AuthError((2,_socks5autherrors[2]))
else:
raise GeneralProxyError((1,_generalerrors[1]))
# Now we can request the actual connection
req = "\x05\x01\x00"
# If the given destination address is an IP address, we'll
# use the IPv4 address request even if remote resolving was specified.
try:
ipaddr = socket.inet_aton(destaddr)
req = req + "\x01" + ipaddr
except socket.error:
# Well it's not an IP number, so it's probably a DNS name.
if self.__proxy[3]==True:
# Resolve remotely
ipaddr = None
req = req + "\x03" + chr(len(destaddr)) + destaddr
else:
# Resolve locally
ipaddr = socket.inet_aton(socket.gethostbyname(destaddr))
req = req + "\x01" + ipaddr
req = req + struct.pack(">H",destport)
self.sendall(req)
# Get the response
resp = self.__recvall(4)
if resp[0] != "\x05":
self.close()
raise GeneralProxyError((1,_generalerrors[1]))
elif resp[1] != "\x00":
# Connection failed
self.close()
if ord(resp[1])<=8:
raise Socks5Error((ord(resp[1]),_generalerrors[ord(resp[1])]))
else:
raise Socks5Error((9,_generalerrors[9]))
# Get the bound address/port
elif resp[3] == "\x01":
boundaddr = self.__recvall(4)
elif resp[3] == "\x03":
resp = resp + self.recv(1)
boundaddr = self.__recvall(ord(resp[4]))
else:
self.close()
raise GeneralProxyError((1,_generalerrors[1]))
boundport = struct.unpack(">H",self.__recvall(2))[0]
self.__proxysockname = (boundaddr,boundport)
if ipaddr != None:
self.__proxypeername = (socket.inet_ntoa(ipaddr),destport)
else:
self.__proxypeername = (destaddr,destport)
def getproxysockname(self):
"""getsockname() -> address info
Returns the bound IP address and port number at the proxy.
"""
return self.__proxysockname
def getproxypeername(self):
"""getproxypeername() -> address info
Returns the IP and port number of the proxy.
"""
return _orgsocket.getpeername(self)
def getpeername(self):
"""getpeername() -> address info
Returns the IP address and port number of the destination
machine (note: getproxypeername returns the proxy)
"""
return self.__proxypeername
def __negotiatesocks4(self,destaddr,destport):
"""__negotiatesocks4(self,destaddr,destport)
Negotiates a connection through a SOCKS4 server.
"""
# Check if the destination address provided is an IP address
rmtrslv = False
try:
ipaddr = socket.inet_aton(destaddr)
except socket.error:
# It's a DNS name. Check where it should be resolved.
if self.__proxy[3]==True:
ipaddr = "\x00\x00\x00\x01"
rmtrslv = True
else:
ipaddr = socket.inet_aton(socket.gethostbyname(destaddr))
# Construct the request packet
req = "\x04\x01" + struct.pack(">H",destport) + ipaddr
# The username parameter is considered userid for SOCKS4
if self.__proxy[4] != None:
req = req + self.__proxy[4]
req = req + "\x00"
# DNS name if remote resolving is required
# NOTE: This is actually an extension to the SOCKS4 protocol
# called SOCKS4A and may not be supported in all cases.
if rmtrslv==True:
req = req + destaddr + "\x00"
self.sendall(req)
# Get the response from the server
resp = self.__recvall(8)
if resp[0] != "\x00":
# Bad data
self.close()
raise GeneralProxyError((1,_generalerrors[1]))
if resp[1] != "\x5A":
# Server returned an error
self.close()
if ord(resp[1]) in (91,92,93):
self.close()
raise Socks4Error((ord(resp[1]),_socks4errors[ord(resp[1])-90]))
else:
raise Socks4Error((94,_socks4errors[4]))
# Get the bound address/port
self.__proxysockname = (socket.inet_ntoa(resp[4:]),struct.unpack(">H",resp[2:4])[0])
if rmtrslv != None:
self.__proxypeername = (socket.inet_ntoa(ipaddr),destport)
else:
self.__proxypeername = (destaddr,destport)
def __negotiatehttp(self,destaddr,destport):
"""__negotiatehttp(self,destaddr,destport)
Negotiates a connection through an HTTP server.
"""
# If we need to resolve locally, we do this now
if self.__proxy[3] == False:
addr = socket.gethostbyname(destaddr)
else:
addr = destaddr
self.sendall("CONNECT " + addr + ":" + str(destport) + " HTTP/1.1\r\n" + "Host: " + destaddr + "\r\n\r\n")
# We read the response until we get the string "\r\n\r\n"
resp = self.recv(1)
while resp.find("\r\n\r\n")==-1:
resp = resp + self.recv(1)
# We just need the first line to check if the connection
# was successful
statusline = resp.splitlines()[0].split(" ",2)
if statusline[0] not in ("HTTP/1.0","HTTP/1.1"):
self.close()
raise GeneralProxyError((1,_generalerrors[1]))
try:
statuscode = int(statusline[1])
except ValueError:
self.close()
raise GeneralProxyError((1,_generalerrors[1]))
if statuscode != 200:
self.close()
raise HTTPError((statuscode,statusline[2]))
self.__proxysockname = ("0.0.0.0",0)
self.__proxypeername = (addr,destport)
def connect(self,destpair):
"""connect(self,despair)
Connects to the specified destination through a proxy.
destpar - A tuple of the IP/DNS address and the port number.
(identical to socket's connect).
To select the proxy server use setproxy().
"""
# Do a minimal input check first
if (type(destpair) in (list,tuple)==False) or (len(destpair)<2) or (type(destpair[0])!=str) or (type(destpair[1])!=int):
raise GeneralProxyError((5,_generalerrors[5]))
if self.__proxy[0] == PROXY_TYPE_SOCKS5:
if self.__proxy[2] != None:
portnum = self.__proxy[2]
else:
portnum = 1080
_orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatesocks5(destpair[0],destpair[1])
elif self.__proxy[0] == PROXY_TYPE_SOCKS4:
if self.__proxy[2] != None:
portnum = self.__proxy[2]
else:
portnum = 1080
_orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatesocks4(destpair[0],destpair[1])
elif self.__proxy[0] == PROXY_TYPE_HTTP:
if self.__proxy[2] != None:
portnum = self.__proxy[2]
else:
portnum = 8080
_orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatehttp(destpair[0],destpair[1])
elif self.__proxy[0] == None:
_orgsocket.connect(self,(destpair[0],destpair[1]))
else:
raise GeneralProxyError((4,_generalerrors[4]))
Loading…
Cancel
Save