python 爬虫下载图片

python3

import urllib.request as ur

s=ur.urlopen('https://www.zhihu.com')

sl=s.read()

from bs4 import BeautifulSoup

bsObj = BeautifulSoup(s.read())

print(bsObj.h1)

bsObj.link['href']

path='/Users/huangyong/Downloads/py/img.png'

f=open(path,"wb")

data=urllib.urlopen(bsObj.link['href']).read()

>>> f.write(data)

f.close()

下载了一张图片

下载百度图片30张，代码：有些是没用的

# -*- coding:utf-8 -*-

import urllib2

import urllib

from bs4 import BeautifulSoup

import re

url = 'https://image.baidu.com/search/index?ct=201326592&cl=2&st=-1&lm=-1&nc=1&ie=utf-8&tn=baiduimage&ipn=r&rps=1&pv=&fm=rs5&word=仙剑奇侠传电视剧&oriquery=仙剑奇侠传&ofr=仙剑奇侠传'

response = urllib2.urlopen(url)

cont = response.read()

#bsObj = BeautifulSoup(cont)

#print(bsObj.li)

#print(bsObj.li.string)

#print(bsObj.find('a', class_='pull-rs'))

#print(bsObj.find('a', class_='pull-rs')['title'])

#print(bsObj.select("pageNum"))

picurl = re.findall('"objURL":"(.*?)"',cont)

i = 0

#print(picurl[0])

print "共提取"+str(len(picurl))+"个图片"

#print len(picurl)

for each in picurl:

i = i + 1

f=open('./py/仙剑奇侠传'+str(i)+'.jpg', 'w+')

data=urllib.urlopen(each).read()

f.write(data)

f.close()

data=None

print(str(i)+'....')

print('over')