import urllib.request
from bs4 import BeautifulSoup
class Scraper:
def __init__(self,
site):
self.site = site
def scrape(self):
r = urllib.request.urlopen(self.site)
html = r.read()
parser = "html.parser"
sp = BeautifulSoup(html,parser)
for tag in sp.find_all("a"):
url = tag.get("href")
if url is None:
continue
if "html" in url:
print("\n" + url)
news = "https://news.google.com/"
Scraper(news).scrape()
《python无师自通》第十九章 版本控制
最新推荐文章于 2023-12-02 23:01:08 发布