#開始導(dǎo)入我們爬取過(guò)程中要使用的包

import urllib.request

import osfrom bs4

import BeautifulSoup

def getSrc(url):

#先讀取出我們要爬取的網(wǎng)址信息

headers = ("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36")

opener = urllib.request.build_opener()

opener.addheaders = [headers]

res = urllib.request.urlopen(url)

html = res.read()

#構(gòu)建一個(gè)BeautifulSoup對(duì)象

soup = BeautifulSoup(html,'html.parser', from_encoding='utf-8')

#找出所以'img class="BDE_Image"'標(biāo)簽對(duì)應(yīng)的值 result = soup.find_all('img',class_="BDE_Image")

links = []

for content in result: s = content['src']

????if s is None:

????????continue

????else:

????????links.append(s)

#輸出一共找出幾個(gè)符合的圖片地址

print("共有"+str(len(links))+"張圖片")

return links

def save(path,links=[]):

if(len(links)==0):

print('沒有符合條件的圖片')

return

#判斷本地是否有photo這個(gè)路徑，沒有的話創(chuàng)建一個(gè)

if not os.path.exists(path):

????os.makedirs(path)

#循環(huán)把圖片下載到本地photo路徑下

i = 0

#for循環(huán) 循環(huán)讀取我們爬取到的 圖片地址列表

for link in links:

????i+=1

????filename =path+'/photo'+str(i)+'.jpg'

????with open(filename,'w'):

????????urllib.request.urlretrieve(link,filename)

????????print('正在下載：'+str(link))

print("圖片下載完成")

def doCrew(url,path='path'):

????links=getSrc(url)

????save(path,links)

if __name__ == "__main__":

????# 這個(gè)是要爬取的網(wǎng)站地址

url = 'http://tieba.baidu.com/p/5698856079'

path='photo'

doCrew(url,path)