通過爬取百度貼吧的案例來了解爬蟲的基本使用

from urllib import request
import re

# 定義了一個URL
page = 100
url = "https://tieba.baidu.com/f?kw=%E6%AE%B5%E5%AD%90&ie=utf-8&pn=" + str(page)

try:
    # 定義請求頭
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36
 
'}
    # 定義請求，傳入請求頭
    req = request.Request(url, headers=headers)
    # 開啟網頁
    resp = request.urlopen(req)
    # 列印響應，解碼
    content = resp.read().decode("utf-8")
    print(content)
    # 正則表示式
    pattern=re.compile(r'<a rel="noopener".*?title=(.*?)\s.*?>(.*?)</a>')
    # 匹配html
    items = re.findall(pattern,content)
    
 
for i in items:
        print('標題：'+i[0]+" "+'內容：'+i[1])
except request.URLError as e:
    # 列印響應碼
    if hasattr(e,'code'):
        print(e.code)
    # 列印異常原因
    if hasattr(e,'reason'):
        print(e.reason)