python---爬取图片数千张（分门别类）

目标网址：http://www.netbian.com/

代码（待优化）如下：

#
# date:2021/1/14
# author：eihouwang
# 1.获取分类标签，形成标签网址列表
# 2.单个标签网址单页图片
# 3.单个标签全部页图片
# 4.获取全部标签，全部图片

import re
from urllib.parse import urljoin
import requests
from bs4 import BeautifulSoup
import os
import time

url = "http://www.netbian.com"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 "
                  "Safari/537.36 SE 2.X MetaSr 1.0"}
dirnames=[]
dirs = os.listdir('E:\czxt\')
if len(dirs)>0:
    for x in dirs:
        dirnames.append('E:czxt\'+x+'\')
#print(dirnames)

#请求网页
def get_html(url):
    r = requests.get(url, headers=headers)
    if r.status_code == 200:
        html = r.text
    else:
        return None
    return html

#获取分类标签列表
def get_lable_url_list(url):

    html = get_html(url)
    soup = BeautifulSoup(html, 'html.parser')
    list_a = soup.findAll('a')
    list_url_lable = []
    num = 0
    for i in range(3, 28):
        num += 1
        url_new = urljoin(url, list_a[i]['href'])
        try:
            path = "E:\czxt\" + url_new.split('/')[-2] + "\"
            os.mkdir(path)
            dirnames.append(path)
        except:
            pass
        list_url_lable.append(url_new)
    #print(sorted(list_url_lable))
    #dirnames=sorted(dirnames)
        #print(num, end='-->')
        #print(url_new, path)
    return sorted(list_url_lable),sorted(dirnames)

#获取单页图片
def get_one_page(url,k=0):
    html = get_html(url)
    soup = BeautifulSoup(html, 'html.parser')
    list = soup.findAll('img')
    #print(list)
    for i in list:
        str1 = i['src']
        try:
            if len(str1) >= 89:
                str_list = str1.split('small')
                str_r = str_list[1].split('.')[0][:32] + ".jpg"
                pic_url = str_list[0] + str_r
                path = sorted(dirnames)[k] + str_r
            else:
                pic_url=str1
                path=sorted(dirnames)[k]+str1.split('/')[-1]
            r1 = requests.get(pic_url, headers=headers)
            # print(dirnames)
            #path = sorted(dirnames)[k] + str_r
            print(path)
            store_one_page(path, r1.content)
        except:
            pass


#存储图片
def store_one_page(path, content):
    with open(path, 'wb') as f:
         f.write(content)
         f.close()

#获取单标签网页列表
def get_onelable_url_list(url):
    one_lable_url_list = []
    html = get_html(url)
    try:
        totalpages = re.findall('/span(.*?)>(d+)</a(.*?)class', html)[0][1]  # 获取分类标签下总页数

        for i in range(1, int(totalpages) + 1):
            if i == 1:
                url_new = url
            else:
                url_new = url + 'index_' + str(i) + '.htm'
            one_lable_url_list.append(url_new)
    except:
        pass
    # print(one_lable_url_list)
    return one_lable_url_list


#lable_url_list,dirnames=get_lable_url_list(url)
# get_onelable_url_list(url)
#get_one_page("http://www.netbian.com/rili/")
def main():
    lable_url_list,dirnames = get_lable_url_list(url)
    print(dirnames)
    length=len(lable_url_list)
    #print(lable_url_list[0])
    for k in range(0,length):
        print('正方访问{}---分类标签网址{}'.format(k,lable_url_list[k]))
        one_lable_url_list=get_onelable_url_list(lable_url_list[k])

        for j in one_lable_url_list:
            print('正在获（{}）页资源'.format(j))
            get_one_page(j,k=k)
            print('获取（{}）页资源完毕'.format(j))
main()