宅男看小说代码为本人原创,仅限于学习交流,请勿用于任何商业用途!本人不承担任何法律责任,如涉及侵权问题,请留言告知。importrequestsfrombs4importBeautifulSoupclassdownloader(object):def__init__(self):self.base='http://m.yruan.com'self.article='/article/53567/'self.page='31977800_3.html'self.target=self.base+self.article+self.pagedefget_contents(self):headers={'User-Agent':'Mozilla/5.0(WindowsNT6.1;Win64;x64)AppleWebKit/537.36(KHTML,likeGecko)''Chrome/70.0.3538.67Safari/537.36',}params={'kw':'赵丽颖','pn':'50'}req=requests.get(url=self.target,headers=headers,params=params)#requests.post()req.encoding='utf-8'html=req.textbs=BeautifulSoup(html,'html.parser')#得到一个BeautifulSoup对象#print(bs.prettify())#print(bs.getText())novelcontent=bs.find(name='div',id="novelcontent")print(type(novelcontent))#print(novelcontent.find(name='p').text.replace('\n',''))#print(novelcontent.find(name='p'))print(novelcontent.find(name='p').text.replace('\n\n','\n'))#print(novelcontent.find(name='ul',class_='novelbutton'))next_a=novelcontent.find(name='ul',class_='novelbutton').find(name='p',class_='p1p3').find(name='a')打印(next_a.get('href'))#print(novelcontent)print("current_url:"+self.target)returnself.base+next_a.get('href')if__name__=='__main__':dl=downloader()next_url=dl.get_contents()print("Next_url:"+next_url)
