Mercurial Repositories > eric / file comparison
comparison: eric6/WebBrowser/SafeBrowsing/SafeBrowsingUrl.py
eric6/WebBrowser/SafeBrowsing/SafeBrowsingUrl.py
- branch
- without_py2_and_pyqt4
- changeset 7192
- a22eee00b052
- parent 6942
- 2602857055c5
- child 7229
- 53054eb5b15a
equal
deleted
inserted
replaced
| 7191:960850ec284c | 7192:a22eee00b052 |
|---|---|
| 6 """ | 6 """ |
| 7 Module implementing an URL representation suitable for Google Safe Browsing. | 7 Module implementing an URL representation suitable for Google Safe Browsing. |
| 8 """ | 8 """ |
| 9 | 9 |
| 10 from __future__ import unicode_literals | 10 from __future__ import unicode_literals |
| 11 | |
| 12 try: | |
| 13 import urlparse # Py2 | |
| 14 import urllib # Py2 | |
| 15 except ImportError: | |
| 16 import urllib.parse as urllib | |
| 17 from urllib import parse as urlparse | |
| 18 | 11 |
| 19 import re | 12 import re |
| 20 import posixpath | 13 import posixpath |
| 21 import socket | 14 import socket |
| 22 import struct | 15 import struct |
| 23 import hashlib | 16 import hashlib |
| 17 import urllib.parse | |
| 24 | 18 |
| 25 import Preferences | 19 import Preferences |
| 26 | 20 |
| 27 | 21 |
| 28 class SafeBrowsingUrl(object): | 22 class SafeBrowsingUrl(object): |
| 68 @param u URL string to unescape | 62 @param u URL string to unescape |
| 69 @type str | 63 @type str |
| 70 @return unescaped URL string | 64 @return unescaped URL string |
| 71 @rtype str | 65 @rtype str |
| 72 """ | 66 """ |
| 73 uu = urllib.unquote(u) | 67 uu = urllib.parse.unquote(u) |
| 74 if uu == u: | 68 if uu == u: |
| 75 return uu | 69 return uu |
| 76 else: | 70 else: |
| 77 return fullUnescape(uu) | 71 return fullUnescape(uu) |
| 78 | 72 |
| 84 @type str | 78 @type str |
| 85 @return quoted string | 79 @return quoted string |
| 86 @rtype str | 80 @rtype str |
| 87 """ | 81 """ |
| 88 safeChars = '!"$&\'()*+,-./:;<=>?@[\\]^_`{|}~' | 82 safeChars = '!"$&\'()*+,-./:;<=>?@[\\]^_`{|}~' |
| 89 return urllib.quote(s, safe=safeChars) | 83 return urllib.parse.quote(s, safe=safeChars) |
| 90 | 84 |
| 91 url = self.__url.strip() | 85 url = self.__url.strip() |
| 92 url = url.replace('\n', '').replace('\r', '').replace('\t', '') | 86 url = url.replace('\n', '').replace('\r', '').replace('\t', '') |
| 93 url = url.split('#', 1)[0] | 87 url = url.split('#', 1)[0] |
| 94 if url.startswith('//'): | 88 if url.startswith('//'): |
| 95 url = Preferences.getWebBrowser("DefaultScheme")[:-3] + url | 89 url = Preferences.getWebBrowser("DefaultScheme")[:-3] + url |
| 96 if len(url.split('://')) <= 1: | 90 if len(url.split('://')) <= 1: |
| 97 url = Preferences.getWebBrowser("DefaultScheme") + url | 91 url = Preferences.getWebBrowser("DefaultScheme") + url |
| 98 url = quote(fullUnescape(url)) | 92 url = quote(fullUnescape(url)) |
| 99 urlParts = urlparse.urlsplit(url) | 93 urlParts = urllib.parse.parse.urlsplit(url) |
| 100 if not urlParts[0]: | 94 if not urlParts[0]: |
| 101 url = Preferences.getWebBrowser("DefaultScheme") + url | 95 url = Preferences.getWebBrowser("DefaultScheme") + url |
| 102 urlParts = urlparse.urlsplit(url) | 96 urlParts = urllib.parse.parse.urlsplit(url) |
| 103 protocol = urlParts.scheme | 97 protocol = urlParts.scheme |
| 104 host = fullUnescape(urlParts.hostname) | 98 host = fullUnescape(urlParts.hostname) |
| 105 path = fullUnescape(urlParts.path) | 99 path = fullUnescape(urlParts.path) |
| 106 query = urlParts.query | 100 query = urlParts.query |
| 107 if not query and '?' not in url: | 101 if not query and '?' not in url: |
| 182 curPath = '' | 176 curPath = '' |
| 183 for i in range(min(4, len(pathParts))): | 177 for i in range(min(4, len(pathParts))): |
| 184 curPath = curPath + pathParts[i] + '/' | 178 curPath = curPath + pathParts[i] + '/' |
| 185 yield curPath | 179 yield curPath |
| 186 | 180 |
| 187 protocol, addressStr = urllib.splittype(url) | 181 protocol, addressStr = urllib.parse.splittype(url) |
| 188 host, path = urllib.splithost(addressStr) | 182 host, path = urllib.parse.splithost(addressStr) |
| 189 user, host = urllib.splituser(host) | 183 user, host = urllib.parse.splituser(host) |
| 190 host, port = urllib.splitport(host) | 184 host, port = urllib.parse.splitport(host) |
| 191 host = host.strip('/') | 185 host = host.strip('/') |
| 192 seenPermutations = set() | 186 seenPermutations = set() |
| 193 for h in hostPermutations(host): | 187 for h in hostPermutations(host): |
| 194 for p in pathPermutations(path): | 188 for p in pathPermutations(path): |
| 195 u = '{0}{1}'.format(h, p) | 189 u = '{0}{1}'.format(h, p) |
