Scraping a page - requires BeautifulSoup and Requests

govtrack.py

from bs4 import BeautifulSoup
import requests
url = 'https://www.govtrack.us/congress/members/amy_klobuchar/412242'
page = requests.get(url)
soup = BeautifulSoup(page.text, 'html.parser')

# get a list of all the h2 elements
head_list = soup.find_all('h2')

# loop over the list to find the heading where we start to scrape
for hed in head_list:
    if hed.text == "Enacted Legislation":
        paragraph = hed.next_sibling.next_sibling
        # break out of loop when we find the one heading we want
        break

# .next_sibling is a BeautifulSoup method for Tag objects -
# https://www.crummy.com/software/BeautifulSoup/bs4/doc/

# this is the paragraph that comes after that h2
print(paragraph.text)

# get all the li elements in the ul that comes after THAT paragraph
leg_list = paragraph.next_sibling.next_sibling.find_all('li')

for item in leg_list:
    print(item.text)

Tested and updated 2/13/2020

Tested without changes, 2/25/2021

Tested without changes, 2/14/2022

Tested and updated 2/25/25