python京东图书信息抓取

import requests
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
#京东图书信息抓取
def getImg(isbn):
    url = 'https://search.jd.com/Search?keyword='+isbn+'&enc=utf-8&pvid=ce5ca7fd71e34233be029f688ac48bce'
    ua = UserAgent()
    headers = {'User-Agent':ua.random}
    data = requests.get(url, headers=headers)
    data.encoding = 'utf-8' #乱码转码
    #print(data.text)
    soup = BeautifulSoup(data.text,'lxml')
    img_div = soup.find_all('div',{'class':'p-img'})
    #print(len(img_div))
    imgs = []
    for index in range(len(img_div)):
        imgs.append('http:'+img_div[index].find('img').get('source-data-lazy-img'))
    return imgs

if __name__=='__main__':
    print('京东图书信息抓取开始。。。')
    imgs = getImg('9787533735609')
    print(imgs)
    print('京东网图书信息抓取结束。。。')

 

#以上代码仅供学习交流参考