beautiful soup web scraping code example
Example 1: BeautifulSoup - scraping the link of the website
import requests
from bs4 import BeautifulSoup
page = requests.get('http://www.example.com')
soup = BeautifulSoup(page.content, 'html.parser')
print(soup.select_one('p a').attrs['href']) # get the link of the website
Example 2: 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 3: beautifulsoup python
import bs4 as bs
import urllib.request
source = urllib.request.urlopen('https://pythonprogramming.net/parsememcparseface/').read()
Example 4: 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)