某度tb圖片爬蟲

#encoding:utf-8

import urllib

import urllib.request

from lxml import etree

 

class Spider(object):

def __init__(self):

self.tiebaName="校花"

self.beginPage=1

self.endPage=3

self.url="http://tieba.baidu.com/f?"

self.ua_header = {"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1 Trident/5.0;"}

self.fileName=1

    

    #構造url

def tiebaSpider(self):

for page in range(self.beginPage,self.endPage+1):

pn=(page-1)*50

wo={'pn':pn,'kw':self.tiebaName}

word=urllib.parse.urlencode(wo)

myurl=self.url+word

self.loadPage(myurl)

 

    #爬取頁面內容

def loadPage(self,url):

req=urllib.request.Request(url,headers=self.ua_header)

data=urllib.request.urlopen(req).read()

 

html=etree.HTML(data)

links=html.xpath('//div[@class="threadlist_lz clearfix"]/div/a/@href')

 

for link in links:

link="http://tieba.baidu.com"+link

self.loadImages(link)

 

 

#爬取帖子詳情頁,獲得圖片的鏈接

def loadImages(self,link):

req=urllib.request.Request(link,headers=self.ua_header)

data=urllib.request.urlopen(req).read()

html=etree.HTML(data)

links=html.xpath('//img[@class="BDE_Image"]/@src')

for imageslink in links:

self.writeImages(imageslink)

 

 

#通過圖片所在鏈接,爬取圖片並保存圖片到本地

def writeImages(self,imagesLink):

function(){ //技術指標 http://www.fx61.com/faq/muniu/437.html

print("正在存儲圖片:",self.fileName,"....")

 

image=urllib.request.urlopen(imagesLink).read()

 

#保存圖片到本地

file=open(r"C:\file\img\\"+str(self.fileName)+".jpg","wb")

file.write(image)

 

file.close()

 

self.fileName+=1

 

if __name__ == '__main__':

mySpider=Spider()

 

mySpider.tiebaSpider()


發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章