parsing HTML response
Wed Apr 12 2023 15:18:23 GMT+0000 (Coordinated Universal Time)
Saved by
@adebola
import requests
from bs4 import BeautifulSoup as bs
raw_req = requests.get("http://adebola.pythonanywhere.com").text
soup = bs(raw_req, 'html')
page_code = soup.prettify()
#.prettify will display the html code in a readable and distinct manner.
label_tags = soup.findAll("label")
#.findAll("label") returns a list of all label tags on the page.
link_tags = soup.findAll("a")
#a list of all anchor tags
link= [i["href"] for i in linktags]
#a list containing only the href attributes of the anchor tags.
labels= [i.text for i in labels]
#returns a list of the label texts in the label tags.
content_copyCOPY
Comments