python 爬取煎蛋ooxx妹子圖

煎蛋網妹子圖首頁（http://jandan.net/ooxx），這個鏈接看起來怎么那么邪惡呢？經分析網站隱藏了圖片地址。心一橫，采取曲線路線，成功爬取大量妹子圖~

源碼如下：

import requests
import re
import os
import base64
from urllib.request import urlretrieve


class JianDan:
    def __init__(self):
        self.url_temp = "http://jandan.net/ooxx/page-{}#comments"
        self.header = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36'}

    def get_url_list(self):
        url_list = [self.url_temp.format(page) for page in range(1, 51)]
        return url_list

    def parse_url(self, url):
        try:
            response = requests.get(url, headers=self.header)
            html_str = response.content.decode()
            img_base_urls = re.findall(
                r'<span class="img-hash">(.*?)</span>', html_str)
            img_urls = list(
                map(lambda base_url: "http:" + base64.b64decode(base_url).decode('utf-8'), img_base_urls))
            return img_urls
        except Exception as e:
            print(f"請求目標網站異常：{e}")

    def make_file(self):
        dir_name = '煎蛋IMG'
        get_path = os.getcwd()
        path_dir = get_path + "/" + dir_name
        if not os.path.isdir(path_dir):
            print(f"創建煎{dir_name}文件夾成功")
            os.mkdir(path_dir)
        else:
            print(f"{dir_name}G文件夾已存在創建失敗")
        return path_dir

    def download(self, img_url, file_path):
        file_name = "/" + img_url.split('/')[-1]
        print(f"###### 正在保存 -> {file_name} ")
        try:
            urlretrieve(img_url, file_path + file_name)
            print(f"###### 保存成功 -> {file_name} ")
        except Exception as e:
            print(f'下載圖片失敗：{file_name}')

    def run(self):
        url_list = self.get_url_list()
        file_path = self.make_file()
        for url in url_list:
            print("#### 獲取第{}頁圖片 ####".format(url_list.index(url) + 1))
            img_urls = self.parse_url(url)
            for img_url in img_urls:
                self.download(img_url, file_path)

        print("end...")


if __name__ == '__main__':
    jiandan = JianDan()
    jiandan.run()

執行結果：

初學python與爬蟲，要學習的還很多。煎蛋網以后還會嘗試用更高效的方式來爬取測試的~