🕷️ 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
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
perf: speeding up `find_by_text` and `find_by_regex` by 3%
Karim shoair740ae815c378
diff --git a/scrapling/parser.py b/scrapling/parser.pyindex 9ff36cf..e18c0aa 100644--- a/scrapling/parser.py+++ b/scrapling/parser.py@@ -50,6 +50,9 @@ _whitelisted = {}# Pre-compiled selectors for efficiency_find_all_elements = XPath(".//*")+_find_all_elements_with_spaces = XPath(+ ".//*[normalize-space(text())]"+) # This selector gets all elements with text contentclass Selector(SelectorsGeneration):@@ -1161,10 +1164,7 @@ class Selector(SelectorsGeneration):if not case_sensitive:text = text.lower()- # This selector gets all elements with text content- for node in self.__handle_elements(- self._root.xpath(".//*[normalize-space(text())]")- ):+ for node in self.__handle_elements(_find_all_elements_with_spaces(self._root)):"""Check if element matches given text otherwise, traverse the children tree and iterate"""node_text = node.textif clean_match:@@ -1203,10 +1203,7 @@ class Selector(SelectorsGeneration):"""results = Selectors()- # This selector gets all elements with text content- for node in self.__handle_elements(- self._root.xpath(".//*[normalize-space(text())]")- ):+ for node in self.__handle_elements(_find_all_elements_with_spaces(self._root)):"""Check if element matches given regex otherwise, traverse the children tree and iterate"""node_text = node.textif node_text.re(