Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

fix(TextHandler): correcting `case_sensitive` argument logic

Karim shoair390bd51cb18b
diff --git a/scrapling/core/custom_types.py b/scrapling/core/custom_types.py
index 6e4ef50..30f61e1 100644
--- a/scrapling/core/custom_types.py
+++ b/scrapling/core/custom_types.py
@@ -134,7 +134,7 @@ class TextHandler(str):
check_match: Literal[True],
replace_entities: bool = True,
clean_match: bool = False,
- case_sensitive: bool = False,
+ case_sensitive: bool = True,
) -> bool:
...
@@ -144,26 +144,26 @@ class TextHandler(str):
regex: Union[str, Pattern[str]],
replace_entities: bool = True,
clean_match: bool = False,
- case_sensitive: bool = False,
+ case_sensitive: bool = True,
check_match: Literal[False] = False,
) -> "TextHandlers[TextHandler]":
...
def re(
self, regex: Union[str, Pattern[str]], replace_entities: bool = True, clean_match: bool = False,
- case_sensitive: bool = False, check_match: bool = False
+ case_sensitive: bool = True, check_match: bool = False
) -> Union["TextHandlers[TextHandler]", bool]:
"""Apply the given regex to the current text and return a list of strings with the matches.
:param regex: Can be either a compiled regular expression or a string.
:param replace_entities: if enabled character entity references are replaced by their corresponding character
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
- :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+ :param case_sensitive: if disabled, function will set the regex to ignore letters case while compiling it
:param check_match: used to quickly check if this regex matches or not without any operations on the results
"""
if isinstance(regex, str):
- if not case_sensitive:
+ if case_sensitive:
regex = re.compile(regex, re.UNICODE)
else:
regex = re.compile(regex, flags=re.UNICODE | re.IGNORECASE)
@@ -182,14 +182,14 @@ class TextHandler(str):
return TextHandlers(typing.cast(List[_TextHandlerType], [TextHandler(_replace_entities(s)) for s in results]))
def re_first(self, regex: Union[str, Pattern[str]], default=None, replace_entities: bool = True,
- clean_match: bool = False, case_sensitive: bool = False) -> "TextHandler":
+ clean_match: bool = False, case_sensitive: bool = True) -> "TextHandler":
"""Apply the given regex to text and return the first match if found, otherwise return the default value.
:param regex: Can be either a compiled regular expression or a string.
:param default: The default value to be returned if there is no match
:param replace_entities: if enabled character entity references are replaced by their corresponding character
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
- :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+ :param case_sensitive: if disabled, function will set the regex to ignore letters case while compiling it
"""
result = self.re(regex, replace_entities, clean_match=clean_match, case_sensitive=case_sensitive)
@@ -218,14 +218,14 @@ class TextHandlers(List[TextHandler]):
return typing.cast(_TextHandlerType, TextHandler(lst))
def re(self, regex: Union[str, Pattern[str]], replace_entities: bool = True, clean_match: bool = False,
- case_sensitive: bool = False) -> 'TextHandlers[TextHandler]':
+ case_sensitive: bool = True) -> 'TextHandlers[TextHandler]':
"""Call the ``.re()`` method for each element in this list and return
their results flattened as TextHandlers.
:param regex: Can be either a compiled regular expression or a string.
:param replace_entities: if enabled character entity references are replaced by their corresponding character
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
- :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+ :param case_sensitive: if disabled, function will set the regex to ignore letters case while compiling it
"""
results = [
n.re(regex, replace_entities, clean_match, case_sensitive) for n in self
@@ -233,7 +233,7 @@ class TextHandlers(List[TextHandler]):
return TextHandlers(flatten(results))
def re_first(self, regex: Union[str, Pattern[str]], default=None, replace_entities: bool = True,
- clean_match: bool = False, case_sensitive: bool = False) -> TextHandler:
+ clean_match: bool = False, case_sensitive: bool = True) -> TextHandler:
"""Call the ``.re_first()`` method for each element in this list and return
the first result or the default value otherwise.
@@ -241,7 +241,7 @@ class TextHandlers(List[TextHandler]):
:param default: The default value to be returned if there is no match
:param replace_entities: if enabled character entity references are replaced by their corresponding character
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
- :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+ :param case_sensitive: if disabled, function will set the regex to ignore letters case while compiling it
"""
for n in self:
for result in n.re(regex, replace_entities, clean_match, case_sensitive):
diff --git a/scrapling/parser.py b/scrapling/parser.py
index 5a4d4f5..e6b138a 100644
--- a/scrapling/parser.py
+++ b/scrapling/parser.py
@@ -763,25 +763,25 @@ class Adaptor(SelectorsGeneration):
return self.get_all_text(strip=True).json()
def re(self, regex: Union[str, Pattern[str]], replace_entities: bool = True,
- clean_match: bool = False, case_sensitive: bool = False) -> TextHandlers:
+ clean_match: bool = False, case_sensitive: bool = True) -> TextHandlers:
"""Apply the given regex to the current text and return a list of strings with the matches.
:param regex: Can be either a compiled regular expression or a string.
:param replace_entities: if enabled character entity references are replaced by their corresponding character
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
- :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+ :param case_sensitive: if disabled, function will set the regex to ignore letters case while compiling it
"""
return self.text.re(regex, replace_entities, clean_match, case_sensitive)
def re_first(self, regex: Union[str, Pattern[str]], default=None, replace_entities: bool = True,
- clean_match: bool = False, case_sensitive: bool = False) -> TextHandler:
+ clean_match: bool = False, case_sensitive: bool = True) -> TextHandler:
"""Apply the given regex to text and return the first match if found, otherwise return the default value.
:param regex: Can be either a compiled regular expression or a string.
:param default: The default value to be returned if there is no match
:param replace_entities: if enabled character entity references are replaced by their corresponding character
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
- :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+ :param case_sensitive: if disabled, function will set the regex to ignore letters case while compiling it
"""
return self.text.re_first(regex, default, replace_entities, clean_match, case_sensitive)
@@ -1009,14 +1009,14 @@ class Adaptors(List[Adaptor]):
return self.__class__(flatten(results))
def re(self, regex: Union[str, Pattern[str]], replace_entities: bool = True,
- clean_match: bool = False, case_sensitive: bool = False) -> TextHandlers[TextHandler]:
+ clean_match: bool = False, case_sensitive: bool = True) -> TextHandlers[TextHandler]:
"""Call the ``.re()`` method for each element in this list and return
their results flattened as List of TextHandler.
:param regex: Can be either a compiled regular expression or a string.
:param replace_entities: if enabled character entity references are replaced by their corresponding character
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
- :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+ :param case_sensitive: if disabled, function will set the regex to ignore letters case while compiling it
"""
results = [
n.text.re(regex, replace_entities, clean_match, case_sensitive) for n in self
@@ -1024,7 +1024,7 @@ class Adaptors(List[Adaptor]):
return TextHandlers(flatten(results))
def re_first(self, regex: Union[str, Pattern[str]], default=None, replace_entities: bool = True,
- clean_match: bool = False, case_sensitive: bool = False) -> TextHandler:
+ clean_match: bool = False, case_sensitive: bool = True) -> TextHandler:
"""Call the ``.re_first()`` method for each element in this list and return
the first result or the default value otherwise.
@@ -1032,7 +1032,7 @@ class Adaptors(List[Adaptor]):
:param default: The default value to be returned if there is no match
:param replace_entities: if enabled character entity references are replaced by their corresponding character
:param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
- :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+ :param case_sensitive: if disabled, function will set the regex to ignore letters case while compiling it
"""
for n in self:
for result in n.re(regex, replace_entities, clean_match, case_sensitive):