Web Scraper in Python

web-scraper.py

from lxml import html
import requests

# 1. Scrape list of medical conditions
page = requests.get('https://www.nhsinform.scot/illnesses-and-conditions/a-to-z')
tree = html.fromstring(page.content)

# Scrape from this content and strip off spaces, tabs, and line breaks
# <h2 class="module__title">
#    Abdominal aortic aneurysm
# </h2>
illnesses = tree.xpath('//h2[@class="module__title"]/text()')
for e in illnesses:
    print(e.replace("\r\n\t", "").replace("\t", ""))