python 模拟搜索应用并爬取应用图片

深碍√TFBOYSˉ_ 2022-04-18 01:10 170阅读 0赞

模拟搜索某个应用名，并爬取应用名和图片下载到本地

也可以从excel表中数据来模拟

#!/usr/bin/env python
    
    # -*- coding: utf-8 -*-
    import requests
    from selenium import webdriver
    from selenium.webdriver.common.by import By
    from time import sleep
    from lxml import etree
    import urllib3
    import re
    import urllib
    import urllib.request
    import xlrd
    
    wb = xlrd.open_workbook(r'C:/Users/Administrator/PycharmProjects/untitled/gxd/search_logo/search_app_logo.xls')
    sh = wb.sheet_by_index(0)  # 第一个表
    rowName = sh.row_values(0)#读取一行的数据
    colName = sh.col_values(4)#读取一列的数据
    row = len(colName)#读取行数
    col = len(rowName)#读取列数
    print(col,row)
    for i in range(0,row+1):
        if colName[i] == '':
            print()
        else:
            # search_app_name = input(('输入要搜索的应用名:'))
            driver = webdriver.Chrome()
            driver.get("https://sj.qq.com/myapp/")
            sleep(1)
            driver.find_element_by_id("J_MainInput").clear()
            driver.find_element_by_id("J_MainInput").send_keys(colName[i])
            driver.find_element_by_id("J_SearchBtn").click()
            sleep(1)
            now_url = driver.current_url
            headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36;'
               }
            response = requests.get(now_url,headers=headers)
            r = response.text
            html = etree.HTML(r,etree.HTMLParser())
            r1 = driver.find_element_by_xpath('//*[@id="J_SearchDefaultListBox"]/li[1]/div[1]/div[1]/div[1]/a/img').get_attribute('src')
            r2 = driver.find_element_by_xpath('//*[@id="J_SearchDefaultListBox"]/li[1]/div[1]/div[2]/div[1]/div[1]/a').text
            if r2 == colName[i]:
                urllib.request.urlretrieve(r1,'%s.jpg' %r2)
                print("搜索结果 ",r2," 存储成功")
            elif colName[i] in r2:
                print("搜索名字与结果不符,但是包容,当前搜索结果为 ",r2," 要存储吗  Y/N")
                p = input('')
                if p=='Y':
                    urllib.request.urlretrieve(r1,'%s.jpg' %r2)
                    print("搜索结果 ", r2, " 存储成功")
                else:
                    print("请手动搜索",colName[i])
            else:
                print("搜索名字与结果不符,请手动搜索",colName[i])
            driver.close()