web data scraping python code example
Example 1: web scraping python
import os
import requests
from bs4 import BeautifulSoup
url = "https://www.google.com/"
reponse = requests.get(url)
if reponse.ok:
soup = BeautifulSoup(reponse.text, "lxml")
title = str(soup.find("title"))
title = title.replace("<title>", "")
title = title.replace("</title>", "")
print("The title is : " + str(title))
os.system("pause")
Example 2: web scraping python
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 3: web scraper python
def simple_get(url):
"""
Attempts to get the content at `url` by making an HTTP GET request.
If the content-type of response is some kind of HTML/XML, return the
text content, otherwise return None.
"""
try:
with closing(get(url, stream=True)) as resp:
if is_good_response(resp):
return resp.content
else:
return None
except RequestException as e:
log_error('Error during requests to {0} : {1}'.format(url, str(e)))
return None
def is_good_response(resp):
"""
Returns True if the response seems to be HTML, False otherwise.
"""
content_type = resp.headers['Content-Type'].lower()
return (resp.status_code == 200
and content_type is not None
and content_type.find('html') > -1)
def log_error(e):
"""
It is always a good idea to log errors.
This function just prints them, but you can
make it do anything.
"""
print(e)