关于BeautifulSoup :
soup.find_all(class_='v_picConBox mt15')
tag.find("div",{"class": "pic"})
pic.img['data-src']
title =text.span.em.a['title']
#coding=utf-8
import re,os
from urllib.request import urlretrieve
import requests
from bs4 import BeautifulSoup
def geturl(url):
html=requests.get(url).content
soup=BeautifulSoup(html,'lxml')
return soup
#抓取电影海报
soup=geturl('http://dianying.2345.com/list/kehuan------.html')
bookAlbum=soup.title.string.split('_')[0]
# print(bookAlbum)
tags=soup.find_all(class_='v_picConBox mt15')
# print(tags)
movies=[]
for tag in tags[0].find_all('li'):
pic= tag.find("div",{"class": "pic"})
if pic is None:
continue
text = tag.find("div",{"class": "txtPadding"})
img_url = pic.img['data-src']
title =text.span.em.a['title']
# print(title,img_url)
movies.append([title,img_url])
print(movies)
if not os.path.exists(bookAlbum):
os.makedirs(bookAlbum)
for movie in movies:
filename=os.path.join(bookAlbum,movie[0]+'.png')
print(filename)
with open(filename,'w') as f:
urlretrieve('http:'+movie[1],filename)
{var%20f='http://v.t.sina.com.cn/share/share.php?appkey=1515056452',u=z||d.location,p=['&url=',e(u),'&title=',e(t||d.title),'&source=',e(r),'&sourceUrl=',e(l),'&content=',c||'gb2312','&pic=',e(p||'')].join('');function%20a(){if(!window.open([f,p].join(''),'mb',['toolbar=0,status=0,resizable=1,width=440,height=430,left=',(s.width-440)/2,',top=',(s.height-430)/2].join('')))u.href=[f,p].join('');};if(/Firefox/.test(navigator.userAgent))setTimeout(a,0);else%20a();})(screen,document,encodeURIComponent,'','','https://www.xiaopingtou.cn//data/attach/topic/topicKPo7gB.jpg', '推荐 bg19910709 的文章《【Python】抓取电影海报并下载》','https://www.xiaopingtou.net/article-62905.html','页面编码gb2312|utf-8默认gb2312'));){kind=link}
