Last active
August 17, 2023 20:55
-
-
Save GuyMicciche/c67953ac9cffc2347cf8dbe96d64cba2 to your computer and use it in GitHub Desktop.
Extract the content of the second h2 tag from the list of all h2 contents
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from html.parser import HTMLParser | |
class MyHTMLParser(HTMLParser): | |
def __init__(self): | |
super().__init__() | |
self.recording = False | |
self.current_data = [] | |
self.all_h2_contents = [] | |
def handle_starttag(self, tag, attrs): | |
if tag == 'h2': | |
self.recording = True | |
self.current_data = [] # Clear current data for new h2 tag | |
def handle_endtag(self, tag): | |
if self.recording and tag == 'h2': | |
self.recording = False | |
self.all_h2_contents.append(''.join(self.current_data).strip()) | |
def handle_data(self, data): | |
if self.recording: | |
self.current_data.append(data) | |
parser = MyHTMLParser() | |
parser.feed(inputData['htmlContent']) | |
# Extract the content of the second h2 tag from the list of all h2 contents | |
extractedText = parser.all_h2_contents[1] if len(parser.all_h2_contents) > 1 else 'Not Found' | |
return {'extractedText': extractedText} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment