# 爬取妹子图

import requests

import os

from bs4 import BeautifulSoup

MZITU = 'https://www.mzitu.com'

USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36'

HEADERS = {

'User-Agent': USER_AGENT,

'Referer': MZITU}

SAVE_PATH = 'D:\妹子图\\'

def get_request(url):

res = requests.get(url, headers=HEADERS)

print("正在请求 " + url)

return res

def get_request_soup(url):

html = get_request(url).text

print("正在解析 ")

return BeautifulSoup(html, 'lxml')

def get_girl_list(url):

soup = get_request_soup(url)

next_url = soup.find(class_='next page-numbers').get('href')

girls = soup.find(class_='postlist').select('li')

for girl in girls:

url = girl.find('a').get('href')

name = girl.find('span').find('a').string

get_girl_group(url, 1, name)

if not next_url == "":

get_girl_list(next_url)

def get_girl_group(url, page, name):

soup = get_request_soup(url + "/" + str(page))

max_page = int(soup.find(class_='pagenavi').select('span')[-2].string)

image = soup.find(class_='main-image').find('img').get('src')

save_img(image, name, page)

page += 1

if page < max_page:

get_girl_group(url, page, name)

# 存储妹子图片到本地

def save_img(url, file_name, page):

file_path = SAVE_PATH + file_name

image_path = file_path + "\" + str(page) + ".jpg"

print('检查文件是否存在 ' + image_path)

if not os.path.exists(image_path):

print("文件正在下载...")

html = get_request(url).content

print("下载成功")

print("检查文件夹是否存在")

exi = os.path.exists(file_path)

if not exi:

print("创建文件夹 " + file_name)

os.makedirs(file_path)

else:

print("文件夹已存在 " + file_name)

print("存入磁盘中...")

f = open(image_path, 'wb')

f.write(html)

print("存放完成")

f.close()

else:

print("文件已存在，无需重复下载" + image_path)

get_girl_list(MZITU)