from urllib import request import re if __name__ == '__main__': urlList = list() f = open("D:\\xiaoshiuo.txt",'w') for i in range(1460216,1463703): url = "http://www.biquyun.com/2_2499/"+str(i)+".html" urlList.append(url) header = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36'} for item in urlList: res = request.Request(url=item,data=None,headers=header) try: rsp = request.urlopen(res) html = rsp.read().decode("gbk") #print(html) head = re.search(r'<div class="bookname">(.*)</div>',html,re.S) try: head = re.search(r'<h1>(.*)</h1>',head.group(),re.S) print(head.group(1)) f.write(" "*10+head.group(1)+'\n') try: text = re.search(r'<div id="content">(.*)</div>', html, re.S) lineList = re.finditer(r' (.*)<br />', html, re.I) for line in lineList: #print(line.group(1)) f.write(line.group(1)+'\n') # print(text.group()) except Exception as e: pass except Exception as e: pass except Exception as e: print(e) f.close()
python爬取小说
最新推荐文章于 2024-02-20 15:45:52 发布