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

Small adjustment to stackoverflow example

Karim shoair4ca41c9dd80e
diff --git a/docs/Examples/selectorless_stackoverflow.py b/docs/Examples/selectorless_stackoverflow.py
index 3f4a341..f54007c 100644
--- a/docs/Examples/selectorless_stackoverflow.py
+++ b/docs/Examples/selectorless_stackoverflow.py
@@ -11,13 +11,15 @@ page = Adaptor(response.text, url=response.url)
# First we will extract the first question title and its author based on the text content
first_question_title = page.find_by_text('Run Selenium Python Script on Remote Server')
first_question_author = page.find_by_text('Ryan')
-# If you want you can extract other questions tags like below
-first_question = first_question_title.find_ancestor(
- lambda ancestor: ancestor.attrib.get('id') and 'question-summary' in ancestor.attrib.get('id')
-)
-rest_of_questions = first_question.find_similar()
-# But since nothing to rely on to extract other titles/authors from these elements without CSS/XPath selectors due to the website nature
-# We will get all the rest of the titles/authors in the page depending on the first title and the first author we got above as a starting point
-for i, (title, author) in enumerate(zip(first_question_title.find_similar(), first_question_author.find_similar()), start=1):
- print(i, title.text, author.text)
+# because this page changes a lot
+if first_question_title and first_question_author:
+ # If you want you can extract other questions tags like below
+ first_question = first_question_title.find_ancestor(
+ lambda ancestor: ancestor.attrib.get('id') and 'question-summary' in ancestor.attrib.get('id')
+ )
+ rest_of_questions = first_question.find_similar()
+ # But since nothing to rely on to extract other titles/authors from these elements without CSS/XPath selectors due to the website nature
+ # We will get all the rest of the titles/authors in the page depending on the first title and the first author we got above as a starting point
+ for i, (title, author) in enumerate(zip(first_question_title.find_similar(), first_question_author.find_similar()), start=1):
+ print(i, title.text, author.text)