freedak/Scrapling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Small adjustment to stackoverflow example

Browse Source
This commit is contained in:
Karim shoair
2024-10-16 19:32:37 +03:00
parent d546b3499b
commit 4ca41c9dd8
1 changed files with 11 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/Examples/selectorless_stackoverflow.py
+11 -9
View File
@@ -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 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_title = page.find_by_text('Run Selenium Python Script on Remote Server')
first_question_author = page.find_by_text('Ryan') first_question_author = page.find_by_text('Ryan')
# If you want you can extract other questions tags like below # because this page changes a lot
first_question = first_question_title.find_ancestor( if first_question_title and first_question_author:
lambda ancestor: ancestor.attrib.get('id') and 'question-summary' in ancestor.attrib.get('id') # If you want you can extract other questions tags like below
) first_question = first_question_title.find_ancestor(
rest_of_questions = first_question.find_similar() lambda ancestor: ancestor.attrib.get('id') and 'question-summary' in ancestor.attrib.get('id')
# 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 rest_of_questions = first_question.find_similar()
for i, (title, author) in enumerate(zip(first_question_title.find_similar(), first_question_author.find_similar()), start=1): # But since nothing to rely on to extract other titles/authors from these elements without CSS/XPath selectors due to the website nature
print(i, title.text, author.text) # 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)