python webscraper code example

Example 1: python web scraping

import requests
from bs4 import BeautifulSoup

URL = 'https://www.monster.com/jobs/search/?q=Software-Developer&where=Australia'
page = requests.get(URL)

soup = BeautifulSoup(page.content, 'html.parser')

Example 2: python web scraping

# basic web scraping with python
# Import libraries
import requests
import urllib.request
import time
from bs4 import BeautifulSoup

# Set the URL you want to webscrape from
url = 'http://web.mta.info/developers/turnstile.html'

# Connect to the URL
response = requests.get(url)

# Parse HTML and save to BeautifulSoup object¶
soup = BeautifulSoup(response.text, "html.parser")

# To download the whole data set, let's do a for loop through all a tags
line_count = 1 #variable to track what line you are on
for one_a_tag in soup.findAll('a'):  #'a' tags are for links
    if line_count >= 36: #code for text files starts at line 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) #pause the code for a sec
    #add 1 for next line
    line_count +=1

Example 3: 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 an exception if we failed to get any data from the url
    raise Exception('Error retrieving contents at {}'.format(url))

Example 4: 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)