Created
August 17, 2023 20:59
-
-
Save GuyMicciche/0b876460a0173086c8a744a0f99b11d4 to your computer and use it in GitHub Desktop.
# Extract the content of the second tabContent div from the list of all tabContent contents
This file contains hidden or 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_tabContent_contents = [] | |
def handle_starttag(self, tag, attrs): | |
if tag == 'div': | |
for name, value in attrs: | |
if name == 'class' and 'tabContent' in value.split(): | |
self.recording = True | |
self.current_data = [] # Clear current data for new tabContent div | |
break | |
def handle_endtag(self, tag): | |
if self.recording and tag == 'div': | |
self.recording = False | |
self.all_tabContent_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 tabContent div from the list of all tabContent contents | |
extractedText = parser.all_tabContent_contents[1] if len(parser.all_tabContent_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