大家好,我是天空之城。今天教大家用xpath爬取图片。
import requests,re,lxml
from lxml import etree
class Spider(object):
def __init__(self):
self.headers = {
'Referer': 'https://www.mzitu.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:46.0) Gecko/20100101 Firefox/46.0',
'cookie': 'Hm_lvt_cb7f29be3c304cd3bb0c65a4faa96c30=1589688375; Hm_lpvt_cb7f29be3c304cd3bb0c65a4faa96c30=1589693220'
}
def getpage(self):
for i in range(100):
url = 'https://www.mzitu.com/page/{}/'.format(str(i))
res=requests.get(url,headers=self.headers)
print(res.status_code)
res1=res.text
html = etree.HTML(res1)
self.getdata(html)
def getdata(self,html):
titles=html.xpath('//ul[@id="pins"]/li/a/img/@alt')
links=html.xpath('//ul[@id="pins"]/li/a/img/@data-original')
for title,link in zip(titles,links):
pic_name = title + '.jpg'
res_pic = requests.get(url=link, headers=self.headers)
try:
with open(pic_name, 'wb') as f:
f.write(res_pic.content)
except Exception:
pass
spider=Spider()
spider.getpage()