代码
# -*- coding:utf-8 -*-
# pip install requests 框架
import requests
# pip install beautifulsoup4 框架
# pip install lxml 解析器
from bs4 import BeautifulSoup
import os
class doutuSpider(object):
headers = {
"user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36"
}
def get_url(self, url):
data = requests.get(url, headers=self.headers)
soup = BeautifulSoup(data.content, 'lxml')
totals = soup.findAll("a", {"class": "list-group-item"})
for one in totals:
sub_url = one.get('href')
global path
path = 'E:\\img' + '\\' + sub_url.split('/')[-1]
os.mkdir(path)
try:
self.get_img_url(sub_url)
except:
pass
pass
pass
def get_img_url(self, url):
data = requests.get(url, headers = self.headers)
soup = BeautifulSoup(data.content, 'lxml')
totals = soup.findAll('div', {'class': 'artile_des'})
for one in totals:
img = one.find('img')
try:
sub_url = img.get('src')
except Exception as e:
raise e
finally:
urls = sub_url
try:
self.get_img(urls)
except:
print urls
pass
pass
pass
def get_img(self, url):
filename = url.split('/')[-1]
global path
img_path = path + '\\' + filename
img = requests.get(url, headers = self.headers)
try:
with open(img_path, 'wb') as f:
f.write(img.content)
except:
pass
pass
def create(self):
for count in range(1,10):
url = 'https://www.doutula.com/article/list/?page={}'.format(count)
print 'download {} page'.format(count)
self.get_url(url)
pass
pass
if __name__ == '__main__':
doutu = doutuSpider()
doutu.create()
