1. 流程分析

1.1 分析目標地址分頁的情況

• 第一頁：https://域名/分類/index.html
• 第二頁：https://域名/分類/index_2.html
• 第三頁：https://域名/分類/index_3.html

即可得出目標分頁的規律

1.2 分析某一頁各個項的特徵

觀察得出每一項的url地址在單頁各個項的ul下面的li中的a標籤中儲存，進入這個url地址即可得到此項中所有圖片的地址

此外這個a標籤的alt屬性中還儲存了此項的摘要描述

1.3 進入某一目標項獲取圖片

通過以上步驟，我們要想獲取圖片的url的路徑，需要訪問每一頁的每一項的URL，這樣即可載入獲取所有圖片的URL地址

拿到圖片地址後儲存，然後即可開啟多執行緒下載圖片

2. 程式碼實現

2.1 程式碼

import os, re
import requests
import logging
from bs4 import BeautifulSoup
from urllib.request import urlretrieve
from concurrent.futures import ThreadPoolExecutor

logging.captureWarnings(True)     # 忽略所有警告資訊

class fuck_photo():
    xxoo = """
             1:  Asian   
             2:  Cartoon 
             3:  Cute    
             4:  Secret 
             5:  Silk   
         
 
"""

    def __init__(self, server, base_url, dirname, thread_num, headers, ):
        self.server = server
        self.base_url = base_url
        self.dirname = dirname
        self.headers = headers
        self.set_path(dirname)
        self.thread_poll = ThreadPoolExecutor(thread_num)
        self.photo_type 
 
= {
            1: "yazhousetu/",
            2: "katong/",
            3: "mengmeizi/",
            4: "zipai/",
            5: "qingchun/",
        }

    def get_page_list(self, target, start_page, max_page):
        """獲取所有頁的url"""
        if start_page <= 1:
            page_list = [target, ]
            print("從第一頁開始爬...")
            start_page += 1
        else:
            page_list = []
        for i in range(start_page, max_page + 1):
            page_link = target[:-5] + "_" + str(i) + ".html"
            page_list.append(page_link)
        print('\n所有圖片會儲存在【%s】資料夾中...\n' % self.dirname)
        return page_list

    def get_list(self, target):
        """獲取每頁所有專案的url"""
        per_page_link_list = []
        response = requests.get(url=target, headers=self.headers, verify=False)
        content = BeautifulSoup(response.text, features="html.parser")
        the_list = content.find('ul', class_='update_area_lists cl').find_all('a')
        for i in the_list:
            per_page_link_list.append(self.server[:-1] + i.get('href'))
        return per_page_link_list

    def get_photo_link_list(self, link_target):
        """獲取某頁中某個項中所有圖片的URL"""
        photo_link_dick = {}
        response = requests.get(url=link_target, headers=self.headers, verify=False)
        content = BeautifulSoup(response.text, features="html.parser")
        the_list = content.find('div', class_='content_left').find_all('img')
        for i in the_list:
            photo_link_dick[i.get('src')] = i.get('alt')
        return photo_link_dick

    def set_path(self, dirname):
        self.dirpath = os.getcwd() + os.sep + dirname
        if not os.path.isdir(self.dirpath):
            os.mkdir(dirname)

    def download_photo(self, photo_links, ret):
        """下載圖片"""
        try:
            # filename = re.findall('/(\w*?\.jpg)', photo_links)[0]
            filename = re.findall('/(\w*?\.jpg)', photo_links)[0][-12:]
            path = self.dirpath + os.sep + ret[photo_links] + filename
            urlretrieve(photo_links, path)
        except Exception as e:
            print("sorry，圖片下載時出現了一個錯誤: %s \n【已忽略...】" % e)
            pass

    def download_thread(self, i):
        ret = photo.get_photo_link_list(i)
        for item in ret:
            self.thread_poll.submit(photo.download_photo, item, ret)

    def start_fuck(self):
        type_num = int(input(self.xxoo + '\n\n' + "請輸入圖片型別："))
        while not type_num:
            print("請輸入對應的數字！" + '\n\n' + self.xxoo)
            type_num = int(input("請輸入圖片型別："))
        target = self.base_url + self.photo_type.get(type_num) + 'index.html'
        startpage = int(input("從哪一頁開始:"))
        maxpage = int(input("到哪一頁為止:"))

        # 獲取指定範圍內所有項的URL
        all_page_list = self.get_page_list(target, startpage, maxpage)
        for item in all_page_list:
            try:
                content_list = photo.get_list(item)
                for i in content_list:
                    photo.download_thread(i)
            except Exception as e:
                print("出現了一個錯誤: %s \n【已忽略】" % e)
                pass


if __name__ == '__main__':
    photo = fuck_photo(
        "https://htx5.com/",        # 目標主機
        "https://htx5.com/",        # 目標地址
        "精美桌布",                  # 設定儲存圖片的目錄，更改爬取型別時，要修改這裡的目錄名稱
        64,                         # 執行緒數
        {                           # 配置請求頭
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0',
            'Referer': "https://htu5.com/",
        }
    )
    photo.start_fuck()

2.2 執行效果