scrape with beautifulsoup code example

Example 1: BeautifulSoup - scraping list from html

from bs4 import BeautifulSoup

# Simple HTML
SIMPLE_HTML = '''<html>
<head></head>
<body>
<h1>This is a title</h1>
<p class="subtitle">Lorem ipsum dolor sit amet.</p>
<p>Here's another p without a class</p>
<ul>
    <li>Sarah</li>
    <li>Mary</li>
    <li>Charlotte</li>
    <li>Carl</li>
</ul>
</body>
</html>'''

simple_soup = BeautifulSoup(SIMPLE_HTML, 'html.parser')      # use html.parser in order to understand the simple HTML

# Find list from html
def find_list():
    list_items = simple_soup.find_all('li')
    my_list = [e.string for e in list_items]  # convert list_items to string
    print(my_list)
    
find_list()

Example 2: Use Beautifulsoup or Scrapy to Scrape a Book Store

import scrapy

class bookScraper(scrapy.Spider):
    name = "bookscrape"
    
    start_urls = [
            'http://books.toscrape.com/'
        ]
    def parse(self, response):
        all_books = response.css('.col-lg-3 ')
    
        for book in all_books:
            img_link = book.css('a img::attr(src)').extract()
            title = book.css('h3 a::attr(title)').extract()
            price = book.css('div.product_price p.price_color::text').extract()

            yield {
                'image_url' : img_link,
                'book_title' : title,
                'product_price' : price
            }
        next_page = response.css('li.next a::attr(href)').get()
        if next_page is not None:
            yield response.follow(next_page, callback = self.parse)

Tags:

Python Example

Recent Posts