抓取妹子图

#!/usr/bin/python
# encoding:utf-8
import requests
from bs4 import BeautifulSoup


url = 'http://www.mzitu.com/all/'


headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36'
}
req = requests.get(url, headers=headers)
soup = BeautifulSoup(req.text, 'lxml')
# print soup


all_a = soup.find('div', class_='all').find_all('a')
for a in all_a:
    title = a.get_text()
    href = a['href']
    # print href
    html = requests.get(href, headers=headers)
    html_soup = BeautifulSoup(html.text, 'lxml')
    max_span = html_soup.find('div', class_='pagenavi').find_all('span')[-2].get_text()
    for page in range(1, int(max_span) + 1):
        page_url = href + '/' + str(page)
        # print page_url
        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']
        # print img_url
        name = img_url[-9:-4]
        img = requests.get(img_url, headers=headers)
        f = open(name + '.jpg', 'ab')
        f.write(img.content)
        f.close()