Answers for "scrapy python web scraping"

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')

python web crawler

import scrapy

class BlogSpider(scrapy.Spider):
    name = 'blogspider'
    start_urls = ['https://blog.scrapinghub.com']

    def parse(self, response):
        for title in response.css('.post-header>h2'):
            yield {'title': title.css('a ::text').get()}

        for next_page in response.css('a.next-posts-link'):
            yield response.follow(next_page, 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

from requests import get
from requests.exceptions import RequestException
from contextlib import closing
from bs4 import BeautifulSoup

web scraper python

>>> raw_html = simple_get('http://www.fabpedigree.com/james/mathmen.htm')
>>> html = BeautifulSoup(raw_html, 'html.parser')
>>> for i, li in enumerate(html.select('li')):
        print(i, li.text)

0  Isaac Newton
 Archimedes
 Carl F. Gauss
 Leonhard Euler
 Bernhard Riemann

1  Archimedes
 Carl F. Gauss
 Leonhard Euler
 Bernhard Riemann

2  Carl F. Gauss
 Leonhard Euler 
 Bernhard Riemann

 3  Leonhard Euler
 Bernhard Riemann

4  Bernhard Riemann

# 5 ... and many more...

web scraper python

def get_hits_on_name(name):
    """
    Accepts a `name` of a mathematician and returns the number
    of hits that mathematician's Wikipedia page received in the 
    last 60 days, as an `int`
    """
    # url_root is a template string that is used to build a URL.
    url_root = 'URL_REMOVED_SEE_NOTICE_AT_START_OF_ARTICLE'
    response = simple_get(url_root.format(name))

    if response is not None:
        html = BeautifulSoup(response, 'html.parser')

        hit_link = [a for a in html.select('a')
                    if a['href'].find('latest-60') > -1]

        if len(hit_link) > 0:
            # Strip commas
            link_text = hit_link[0].text.replace(',', '')
            try:
                # Convert to integer
                return int(link_text)
            except:
                log_error("couldn't parse {} as an `int`".format(link_text))

    log_error('No pageviews found for {}'.format(name))
    return None