Answers for "web scraper using python"

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')

web scraping python

#pip install beautifulsoup4

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")

#python (code name).py

web scraping python

import scrapy
from ..items import SampletestItem #items class

class QuoteTestSpider(scrapy.Spider):
    name = 'quote_test'
    start_urls = ['https://quotes.toscrape.com/']

    def parse(self, response):
        items = SampletestItem() #items class
        quotes = response.css("div.quote")
        for quote in quotes:
            items['title'] = quote.css("span.text::text").get()
            items['author'] = quote.css(".author::text").get()
            items['tags'] = quote.css(".tags .tag::text").getall()
            
            yield items
            next_page = response.css(".next a::attr(href)").get()
            if next_page is not None:
                next_url = response.urljoin(next_page)
                yield scrapy.Request(next_url, callback=self.parse)

web scraping with python

# example of web scraping links using asyncio and using all cores
import asyncio, requests, aiohttp, os
from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor, as_completed
from bs4 import BeautifulSoup as BS

executor = ThreadPoolExecutor(max_workers=8)
loop = asyncio.get_event_loop()

async def make_requests():
    urls = ['http://www.filedropper.com/lister.php?id=0', 'http://www.filedropper.com/lister.php?id=1', 'http://www.filedropper.com/lister.php?id=2', 'http://www.filedropper.com/lister.php?id=3', 'http://www.filedropper.com/lister.php?id=4', 'http://www.filedropper.com/lister.php?id=5', 'http://www.filedropper.com/lister.php?id=6', 'http://www.filedropper.com/lister.php?id=7', 'http://www.filedropper.com/lister.php?id=8', 'http://www.filedropper.com/lister.php?id=9', 'http://www.filedropper.com/lister.php?id=a', 'http://www.filedropper.com/lister.php?id=b', 'http://www.filedropper.com/lister.php?id=c', 'http://www.filedropper.com/lister.php?id=d', 'http://www.filedropper.com/lister.php?id=e', 'http://www.filedropper.com/lister.php?id=f', 'http://www.filedropper.com/lister.php?id=g', 'http://www.filedropper.com/lister.php?id=h', 'http://www.filedropper.com/lister.php?id=i', 'http://www.filedropper.com/lister.php?id=j', 'http://www.filedropper.com/lister.php?id=k', 'http://www.filedropper.com/lister.php?id=l', 'http://www.filedropper.com/lister.php?id=m', 'http://www.filedropper.com/lister.php?id=n', 'http://www.filedropper.com/lister.php?id=o', 'http://www.filedropper.com/lister.php?id=p', 'http://www.filedropper.com/lister.php?id=q', 'http://www.filedropper.com/lister.php?id=r', 'http://www.filedropper.com/lister.php?id=s', 'http://www.filedropper.com/lister.php?id=t', 'http://www.filedropper.com/lister.php?id=u', 'http://www.filedropper.com/lister.php?id=v', 'http://www.filedropper.com/lister.php?id=w', 'http://www.filedropper.com/lister.php?id=x', 'http://www.filedropper.com/lister.php?id=y', 'http://www.filedropper.com/lister.php?id=z']

    futures = [loop.run_in_executor(executor, requests.get, url) for url in urls]
    await asyncio.wait(futures)

    for future in futures:
        soup = BS(future.result().content)
        for all_links in soup.find_all('a', href=True):
            print("URL:", all_links['href'])    
            with open('filedropper_com.txt', 'a') as f:
                f.write(all_links['href'] + 'n')

loop.run_until_complete(make_requests())

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))

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)