#--*--coding:utf-8--*-- import re import urllib.request from urllib.error import URLError,HTTPError import sysprint(sys.getdefaultencoding())url = 'http://www.qiushibaike.com/text/page/1' # 給文件加入頭信息，用以模擬瀏覽器訪問 user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)' headers = {'Connection': 'Keep-Alive','Accept': 'text/html, application/xhtml+xml, */*','Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3','User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko' } for i in range(1,30+1):try:#實現翻頁翻頁url = re.sub('page/\d+','page/%d'%i,url,re.S)print(url)#發送請求，獲得返回信息req = urllib.request.Request(url,headers=headers)response = urllib.request.urlopen(req,timeout=5)content = response.read().decode('utf-8')#處理獲取的web網頁，并將信息處理了items = re.findall('<div class="content">(.*?)</div>',content,re.S)length = len(items)for j in range(0,length):#將信息寫入文件中fileHandle = open("qiushibaike2.txt",'a')fileHandle.write(str(j+1)+": ")fileHandle.write(items[j])fileHandle.write("\n")except HTTPError as e:print("HTTPError")except URLError as e:print("URLError")

如果有幫到您，打個賞唄

總結

以上是生活随笔為你收集整理的python爬虫，爬取糗事百科并保存到文件中的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。