第一个爬虫——爬取海报网热门图片

地址：http://pic.haibao.com/hotimage/

网页元素分析：

结果

源码

import requests
from bs4 import BeautifulSoup
import os
import time

def getHotImgs():
    topPage = requests.get("http://pic.haibao.com/hotimage/").content
    topPageParse = BeautifulSoup(topPage,"html5lib")
    allLiTags = topPageParse.find_all('div', class_="pagelibox")
    imgs = []
    for liTag in allLiTags:
        imgTag = liTag.img
        imgSource = imgTag['data-original']
        if imgSource :
            imgs.append(imgSource)
    return imgs

def saveHotImgs(imgs):
    if not os.path.exists('haibaoHotImg'):
        os.mkdir('haibaoHotImg')
    i = 0
    for img in imgs:
        image = requests.get(img).content
        timestamp = timeMillis()
        fileName = str(timestamp)+str(i)
        imgPar = img.rpartition('.')
        fileExt = imgPar[len(imgPar)-1]
        with file("haibaoHotImg"+'/'+fileName+'.'+fileExt,'w') as imgFile:
            imgFile.write(image)

def timeMillis():
    return int(round(time.time() * 1000))

if __name__ == "__main__":
    imgs = getHotImgs()
    saveHotImgs(imgs)
    print "finished"