`from bs4 import BeautifulSoup import requests resp=requests.get('umei.net/meinvtupian…') resp.encoding='utf-8' #解析html main_page=BeautifulSoup(resp.text,'html.parser') #找到某个东西 #find() 找一个 #find_all() 所有 allList=main_page.find('div',attrs={'class','TypeList'}).find_all('a',attrs={'class','TypeBigPics'}) n=0 for a in allList: href=a.get('href') url1='umei.net/'+href resp1=requests.get(url1) resp1.encoding='utf-8' child_page=BeautifulSoup(resp1.text,'html.parser') #找图片路径 src=child_page.find('div',attrs={'class','ImageBody'}).find('img').get('src') n += 1 #图片文件 f=open('img/tu_%s.jpg'%n,mode="wb") f.write(requests.get(src).content) # 向外拿出图片的数据,不是文本信息
print('下载第%d张' % n)
script=child_page.find('div', attrs={'class', 'ImageBody'}).find('img').find_next('script').text
print(script)`