剛接觸python，試一下爬蟲，拿自己的Blog開刀
import requests
from bs4 import BeautifulSoup
import pprint
url = "https://www.cnblogs.com/zyqgold/"
#爬取分頁
def download_all_htmls():
htmls = []
for i in range(7):
url = f"https://www.cnblogs.com/zyqgold/default.html?page={i+1}"
#print("頁面URL:",url)
r = requests.get(url)
if r.status_code != 200:
raise Exception("error")
htmls.append(r.text)
return htmls
#爬取分頁里邊的文章鏈接
def parse_single_html(html):
soup = BeautifulSoup(html,"html.parser")
articles = soup.find_all("a",class_= "postTitle2 vertical-middle")
nodes =[]
for article in articles:
nodes.append({"name":article.span.string,"link":article.attrs["href"]})
return nodes
htmls = download_all_htmls()
all_html = []
for html in htmls:
all_html.extend(parse_single_html(html))
pprint.pprint(all_html)
轉載請註明出處，本文鏈接：https://www.uj5u.com/houduan/271834.html
標籤：Python