python 爬百度图片脚本

功能：自动根据关键词爬取指定页数的图片，并保存在指定目录下（关键词为文件夹名，图片网址为图片名）

参数：word 关键字
begin_page_num 开始页数
end_page_num 结束页数

"""
TODO: 
    funtion: lsp的救赎
    other: 
    author: limenghua
    createTime: 2020-12-25 17:20
"""

import requests
import urllib3
import urllib
import re
import os

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) # fuck安全警告

class LspFighting:

    def __init__(self, word, begin_page_num, end_page_num):
        """
        初始化
        :param word: 搜索关键词
        """
        self.url = "https://image.baidu.com/search/acjson?tn=resultjson_com&logid=11432824844719315390&ipn=rj&" \
                   "ct=&is=&fp=result&queryWord=%E7%BE%8E%E9%A3%9F&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&" \
                   "st=-1&z=&ic=0&hd=&latest=&copyright=&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&" \
                   "expermode=&force=&rn=30&1608887774681=" + "&word=" + word
        self.word = word
        self.headers = { # 请求头
            "User-agent": "Mozilla/5.0",
            "Content-Type": "utf-8",
        }

        self.begin_page_num = begin_page_num  # 开始页数
        self.end_page_num = end_page_num  # 结束页数
        self.page_num = 30 # 每页编号的增加值

    def decode_url(self, url):
        """
        对百度加密后的地址进行解码
        :param url:百度加密的url
        :return:解码后的url
        """
        table = {'w': "a", 'k': "b", 'v': "c", '1': "d", 'j': "e", 'u': "f", '2': "g", 'i': "h",
                 't': "i", '3': "j", 'h': "k", 's': "l", '4': "m", 'g': "n", '5': "o", 'r': "p",
                 'q': "q", '6': "r", 'f': "s", 'p': "t", '7': "u", 'e': "v", 'o': "w", '8': "1",
                 'd': "2", 'n': "3", '9': "4", 'c': "5", 'm': "6", '0': "7",
                 'b': "8", 'l': "9", 'a': "0", '_z2C$q': ":", "_z&e3B": ".", 'AzdH3F': "/"}
        url = re.sub(r'(?P<value>_z2C\$q|_z\&e3B|AzdH3F+)', lambda matched: table.get(matched.group('value')), url)

        return re.sub(r'(?P<value>[0-9a-w])', lambda matched: table.get(matched.group('value')), url)

    def filter_url(self, url):
        """
        过滤不合法的网址
        :param url: url
        :return: bool
        """
        res = re.search(".jpg|.gif|.jpeg|.png", url)

        if res == None:
            return False

        return True

    def run(self):
        """
        对外运行方法
        :return:
        """
        while True:

            if self.begin_page_num > self.end_page_num:
                break

            print("请求第{}页：".format(self.begin_page_num + 1))

            current_page_num = (self.begin_page_num - 1) * self.page_num  # 计算url所需要的翻页参数

            url = self.url + "&pn=" + str(current_page_num) + "&gsm=" + str(hex(current_page_num)) # url拼装翻页

            res = requests.get(url, headers=self.headers, verify=False) # 请求图片资源

            pic_urls = re.findall('"objURL":"(.*?)",', res.text, re.S)  # 正则匹配出需要的url

            if os.path.exists("LearningMaterials/" + self.word + "/") == False:  # 目录不存在就创建
                os.makedirs("LearningMaterials/" + self.word + "/")

            num = 0 # 统计下载数

            for i in range(len(pic_urls)):

                pic_urls[i] = self.decode_url(pic_urls[i]) # 地址解码
                pic_urls[i] = re.search('src=.*?&', pic_urls[i]) # 正则匹配src源地址

                if pic_urls[i] == None: # 跳过没匹配到的
                    continue

                pic_urls[i] = pic_urls[i].group()[4:-1] # 截取源地址src=xxx -> xxx

                if self.filter_url(pic_urls[i]) == False: # 过滤不合法地址
                    continue

                if os.path.exists("LearningMaterials/" + self.word + "/" + pic_urls[i]) == True: # 跳过重复下载
                    continue

                with open("LearningMaterials/" + self.word + "/" + pic_urls[i], 'wb') as pic: # 下载图片
                    url = urllib.parse.unquote(pic_urls[i])
                    res = requests.get(url, headers=self.headers, verify=False)
                    pic.write(res.content)

                num += 1

            print("下载{}条学习资料".format(num))

            self.begin_page_num += 1


if __name__ == '__main__':
    word = "美女" # 搜索关键字
    begin_page_num = 0  # 开始页数
    end_page_num = 3  # 结束页数
    lsp = LspFighting(word, begin_page_num, end_page_num)
    lsp.run()