python - 使用 BeautifulSoup 查找与特定关键字相关的链接

Question

我必须修改此代码，以便抓取 仅保留包含特定关键字的链接。就我而言，我正在抓取报纸页面以查找与“英国脱欧”一词相关的新闻。

我已经尝试修改方法 parse_links 以便它只保留其中包含“Brexit”的链接(或“a”标签)，但它似乎不起作用。

我应该把条件放在哪里？

import requests
from bs4 import BeautifulSoup
from queue import Queue, Empty
from concurrent.futures import ThreadPoolExecutor
from urllib.parse import urljoin, urlparse

class MultiThreadScraper:
 
    def __init__(self, base_url):
 
        self.base_url = base_url
        self.root_url = '{}://{}'.format(urlparse(self.base_url).scheme, urlparse(self.base_url).netloc)
        self.pool = ThreadPoolExecutor(max_workers=20)
        self.scraped_pages = set([])
        self.to_crawl = Queue(10)
        self.to_crawl.put(self.base_url)
 
    def parse_links(self, html):
        soup = BeautifulSoup(html, 'html.parser')
        links = soup.find_all('a', href=True)
        for link in links:
            url = link['href']
            if url.startswith('/') or url.startswith(self.root_url):
                url = urljoin(self.root_url, url)
                if url not in self.scraped_pages:
                    self.to_crawl.put(url)
 
    def scrape_info(self, html):
        return
 
    def post_scrape_callback(self, res):
        result = res.result()
        if result and result.status_code == 200:
            self.parse_links(result.text)
            self.scrape_info(result.text)
 
    def scrape_page(self, url):
        try:
            res = requests.get(url, timeout=(3, 30))
            return res
        except requests.RequestException:
            return
 
    def run_scraper(self):
        while True:
            try:
                target_url = self.to_crawl.get(timeout=60)
                if target_url not in self.scraped_pages:
                    print("Scraping URL: {}".format(target_url))
                    self.scraped_pages.add(target_url)
                    job = self.pool.submit(self.scrape_page, target_url)
                    job.add_done_callback(self.post_scrape_callback)
            except Empty:
                return
            except Exception as e:
                print(e)
                continue
if __name__ == '__main__':
    s = MultiThreadScraper("https://elpais.com/")
    s.run_scraper()

Answer 1

你需要导入re模块来获取具体的文本值。试试下面的代码。

import re
 links = soup.find_all('a', text=re.compile("Brexit"))

这应该返回仅包含 Brexit 的链接。