web scrapper pythpn code example
Example 1: python web scraping
import requests
import urllib.request
import time
from bs4 import BeautifulSoup
url = 'http://web.mta.info/developers/turnstile.html'
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
line_count = 1
for one_a_tag in soup.findAll('a'):
if line_count >= 36:
link = one_a_tag['href']
download_url = 'http://web.mta.info/developers/'+ link
urllib.request.urlretrieve(download_url,'./'+link[link.find('/turnstile_')+1:])
time.sleep(1)
line_count +=1
Example 2: web scraper python
def get_names():
"""
Downloads the page where the list of mathematicians is found
and returns a list of strings, one per mathematician
"""
url = 'http://www.fabpedigree.com/james/mathmen.htm'
response = simple_get(url)
if response is not None:
html = BeautifulSoup(response, 'html.parser')
names = set()
for li in html.select('li'):
for name in li.text.split('\n'):
if len(name) > 0:
names.add(name.strip())
return list(names)
raise Exception('Error retrieving contents at {}'.format(url))