1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
| import requests
from bs4 import BeautifulSoup
headers = {'User-Agent':"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
all_url = 'http://www.mzitu.com/all'
start_html = requests.get(all_url, headers=headers)
Soup = BeautifulSoup(start_html.text, 'lxml')
all_a = Soup.find('div', class_='all').find_all('a')
for a in all_a:
title = a.get_text()
href = a.get('href')
html = requests.get(href, headers=headers)
html_Soup = BeautifulSoup(html.text, 'lxml')
max_span = html_Soup.findAll('span')[10].get_text()
for page in range(1, int(max_span) + 1):
page_url = href + '/' + str(page)
img_html = requests.get(page_url, headers=headers)
img_Soup = BeautifulSoup(img_html.text, 'lxml')
img_url = img_Soup.find('div', class_='main-image').find('img')['src']
name = img_url[-9:-4]
img = requests.get(img_url, headers=headers)
f = open(name + '.jpg', 'ab')
f.write(img.content)
f.close()
|