Mercurial Repositories > eric / file comparison
comparison: eric6/WebBrowser/AdBlock/AdBlockRule.py
eric6/WebBrowser/AdBlock/AdBlockRule.py
- changeset 7775
- 4a1db75550bd
- parent 7773
- fe42bd17d4fe
- child 7923
- 91e843545d9a
equal
deleted
inserted
replaced
| 7774:9eed155411f0 | 7775:4a1db75550bd |
|---|---|
| 5 | 5 |
| 6 """ | 6 """ |
| 7 Module implementing the AdBlock rule class. | 7 Module implementing the AdBlock rule class. |
| 8 """ | 8 """ |
| 9 | 9 |
| 10 | |
| 11 import re | 10 import re |
| 12 | |
| 13 from enum import IntEnum | 11 from enum import IntEnum |
| 14 | 12 |
| 15 from PyQt5.QtCore import Qt, QRegExp | 13 from PyQt5.QtCore import Qt |
| 16 from PyQt5.QtWebEngineCore import QWebEngineUrlRequestInfo | 14 from PyQt5.QtWebEngineCore import QWebEngineUrlRequestInfo |
| 17 | 15 |
| 18 | 16 |
| 19 def toSecondLevelDomain(url): | 17 def toSecondLevelDomain(url): |
| 20 """ | 18 """ |
| 274 | 272 |
| 275 # Rule is classic regexp | 273 # Rule is classic regexp |
| 276 if parsedLine.startswith("/") and parsedLine.endswith("/"): | 274 if parsedLine.startswith("/") and parsedLine.endswith("/"): |
| 277 parsedLine = parsedLine[1:-1] | 275 parsedLine = parsedLine[1:-1] |
| 278 self.__type = AdBlockRuleType.RegExpMatchRule | 276 self.__type = AdBlockRuleType.RegExpMatchRule |
| 279 self.__regExp = QRegExp(parsedLine, self.__caseSensitivity, | 277 if self.__caseSensitivity: |
| 280 QRegExp.RegExp) | 278 self.__regExp = re.compile(parsedLine) |
| 279 else: | |
| 280 self.__regExp = re.compile(parsedLine, re.IGNORECASE) | |
| 281 self.__stringMatchers = self.__parseRegExpFilter(parsedLine) | 281 self.__stringMatchers = self.__parseRegExpFilter(parsedLine) |
| 282 return | 282 return |
| 283 | 283 |
| 284 # Remove starting / ending wildcards (*) | 284 # Remove starting / ending wildcards (*) |
| 285 if parsedLine.startswith("*"): | 285 if parsedLine.startswith("*"): |
| 300 self.__type = AdBlockRuleType.StringEndsMatchRule | 300 self.__type = AdBlockRuleType.StringEndsMatchRule |
| 301 self.__matchString = parsedLine | 301 self.__matchString = parsedLine |
| 302 return | 302 return |
| 303 | 303 |
| 304 # If there is still a wildcard (*) or separator (^) or (|), | 304 # If there is still a wildcard (*) or separator (^) or (|), |
| 305 # the rule must be modified to comply with QRegExp. | 305 # the rule must be modified to comply with re. |
| 306 if "*" in parsedLine or "^" in parsedLine or "|" in parsedLine: | 306 if "*" in parsedLine or "^" in parsedLine or "|" in parsedLine: |
| 307 self.__type = AdBlockRuleType.RegExpMatchRule | 307 self.__type = AdBlockRuleType.RegExpMatchRule |
| 308 pattern = self.__convertPatternToRegExp(parsedLine) | 308 pattern = self.__convertPatternToRegExp(parsedLine) |
| 309 self.__regExp = QRegExp(pattern, self.__caseSensitivity, | 309 if self.__caseSensitivity: |
| 310 QRegExp.RegExp) | 310 self.__regExp = re.compile(pattern) |
| 311 else: | |
| 312 self.__regExp = re.compile(pattern, re.IGNORECASE) | |
| 311 self.__stringMatchers = self.__parseRegExpFilter(parsedLine) | 313 self.__stringMatchers = self.__parseRegExpFilter(parsedLine) |
| 312 return | 314 return |
| 313 | 315 |
| 314 # This rule matches all URLs | 316 # This rule matches all URLs |
| 315 if len(parsedLine) == 0: | 317 if len(parsedLine) == 0: |
| 503 matched = encodedUrl.endswith(self.__matchString) | 505 matched = encodedUrl.endswith(self.__matchString) |
| 504 elif self.__type == AdBlockRuleType.RegExpMatchRule: | 506 elif self.__type == AdBlockRuleType.RegExpMatchRule: |
| 505 if not self.__isMatchingRegExpStrings(encodedUrl): | 507 if not self.__isMatchingRegExpStrings(encodedUrl): |
| 506 matched = False | 508 matched = False |
| 507 else: | 509 else: |
| 508 matched = self.__regExp.indexIn(encodedUrl) != -1 | 510 matched = self.__regExp.search(encodedUrl) is not None |
| 509 elif self.__type == AdBlockRuleType.MatchAllUrlsRule: | 511 elif self.__type == AdBlockRuleType.MatchAllUrlsRule: |
| 510 matched = True | 512 matched = True |
| 511 | 513 |
| 512 return matched | 514 return matched |
| 513 | 515 |
| 1151 Public method to get the regular expression and associated string | 1153 Public method to get the regular expression and associated string |
| 1152 matchers. | 1154 matchers. |
| 1153 | 1155 |
| 1154 @return tuple containing the regular expression and the list of | 1156 @return tuple containing the regular expression and the list of |
| 1155 string matchers | 1157 string matchers |
| 1156 @rtype tuple of (QRegExp, list of str) | 1158 @rtype tuple of (re.Pattern, list of str) |
| 1157 """ | 1159 """ |
| 1158 if self.__regExp is not None: | 1160 if self.__regExp is not None: |
| 1159 return (QRegExp(self.__regExp), self.__stringMatchers[:]) | 1161 return (re.compile(self.__regExp.pattern), |
| 1162 self.__stringMatchers[:]) | |
| 1160 else: | 1163 else: |
| 1161 return (None, []) | 1164 return (None, []) |
| 1162 | 1165 |
| 1163 def copyFrom(self, other): | 1166 def copyFrom(self, other): |
| 1164 """ | 1167 """ |
