爬取《斗破苍穹》小说

headers={'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}
#爬取《斗破苍穹》全文小说
f=open("H:/doupo.txt",'a+')
def get_info(url):
    res=requests.get(url,headers=headers)
    if res.status_code==200:
        contents=re.findall('

(.*?)

',res.content.decode('utf-8'),re.S) for content in contents: f.write(content+"\n") else: pass if __name__=="__main__": urls=['http://www.doupoxs.com/doupocangqiong/{}.html'.format(str(i)) for i in range(2,1665)] for url in urls: get_info(url) time.sleep(1) f.close()

参考教材《从零开始学python网络爬虫》

你可能感兴趣的:(其他)