🕷️ 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
Updating the keywords whitelisting logic in `find`/`find_all` functions
Karim shoairb91953652745
diff --git a/scrapling/parser.py b/scrapling/parser.pyindex f429197..61d4796 100644--- a/scrapling/parser.py+++ b/scrapling/parser.py@@ -551,9 +551,10 @@ class Adaptor(SelectorsGeneration):"""# Attributes that are Python reserved words and can't be used directly# Ex: find_all('a', class="blah") -> find_all('a', class_="blah")+ # https://www.w3schools.com/python/python_ref_keywords.aspwhitelisted = {- 'id_': 'id','class_': 'class',+ 'for_': 'for',}if not args and not kwargs:@@ -582,14 +583,17 @@ class Adaptor(SelectorsGeneration):if not all([(type(k) is str and type(v) is str) for k, v in kwargs.items()]):raise TypeError('Only string values are accepted for arguments')- attributes.update(kwargs)++ for attribute_name, value in kwargs.items():+ # Only replace names for kwargs, replacing them in dictionaries doesn't make sense+ attribute_name = whitelisted.get(attribute_name, attribute_name)+ attributes[attribute_name] = value# It's easier and faster to build a selector than traversing the treetags = tags or ['']for tag in tags:selector = tagfor key, value in attributes.items():- key = whitelisted.get(key, key)value = value.replace('"', r'\"') # Escape double quotes in user input# Not escaping anything with the key so the user can pass patterns like {'href*': '/p/'} or get errors :)selector += '[{}="{}"]'.format(key, value)