一个小爬虫(练手)
509
- ai0by2019-03-21注册会员133975
- 本帖最后由 ai0by 于 2019-3-27 17:04 编辑 *
- # -- coding: utf-8 --
- from bs4 import BeautifulSoup
- import requests
- import urllib2
- import random
- - def spy(url):
- req = urllib2.Request(url)
- req = urllib2.urlopen(req)
- page = req.read()
- soup = BeautifulSoup(page, "html.parser")
- for imgSoup in soup.find_all('div', {"class": "row"}):
- for i in imgSoup.find_all('div', {'class': 'photo'}):
- for j in i.find('div', {'class': 'photo-link-outer'}).find('a').find_all('img'):
- img = j.get("src")
- print img
- str = random.sample('zyxwvutsrqponmlkjihgfedcba', 6)
- downImg(img, str)
- nexturl = soup.find('p',{'class':'go-to-next-page'})
- nexturl = nexturl.find('a').get('href')
- pageurl = "http://jigadori.fkoji.com"+nexturl
- spy(pageurl)
- - def downImg(img,m):
- try:
- r = requests.get(img)
- except Exception , e:
- print "图片获取失败"
- return
- with open('./img/good%s.jpg' % m, 'wb') as f:
- f.write(r.content)
- if __name__ == '__main__':
- url = "http://jigadori.fkoji.com"
- spy(url)复制代码


昨天上午看大佬发的资源没存上,自写了一个,不太完善,好歹算是能看。。。。