【Selenium + Python】之 Excel、CSV、XML文件读取数据并运用数据百度查询

目录

• 从Excel读取数据进行百度搜索

• 从CSV读取数据进行百度搜索

• 从XML读取数据进行登录操作

• 附：其他学习资料（《xml.etree.ElementTree模块》、《python读取xml文件》）

一、从Excel读取数据进行百度搜索

封装读取方法：

import xlrd
from selenium import webdriver
from selenium.webdriver.common.by import By

class rdExcel():
    def __init__(self,excel_dir,sheet_name):
        self.r = []
        self.rd = xlrd.open_workbook(excel_dir)
        self.sh = self.rd.sheet_by_name(sheet_name)
        #首行设置为key
        self.key = self.sh.row_values(0)
        #获取总行数
        self.rownum = self.sh.nrows
        #获取总列数
        self.colnum = self.sh.ncols

    def function(self):
        if self.rownum<=1:
            print("没有获取到数值")
        else:
            r = []
            j=1
            #要执行的行数
            for i in range(self.rownum - 1):
                s = {}
                values = self.sh.row_values(j)
                for x in range(self.colnum):
                    s[self.key[x]] = values[x]
                r.append(s)
                j+=1
            # print(r)
            return r

if __name__ == '__main__':
    a = input("excel_dir:")
    b = input("sheet_name:")
    data = rdExcel(a,b)
    print(data.function())

基本操作：指定单元格读取数据

rd = xlrd.open_workbook("C:\\Users\\ZHANGCH\\Desktop\\test99.xlsx")
sh = rd.sheet_by_name("rdData")

value = sh.row_values(1)[0]
driver = webdriver.Chrome()
driver.maximize_window()
driver.get("http://www.baidu.com")
driver.find_element(By.CSS_SELECTOR,"#kw").send_keys(value)
driver.find_element(By.CSS_SELECTOR,"#su").click()

============================================================================

写法进行修改规整，完整获取指定数据进行百度查询：

写法①：

import xlrd
import os
from selenium import webdriver
from selenium.webdriver.common.by import By
from time import sleep

base = os.path.dirname(os.path.dirname(__file__))
base_dir = base.replace('/','\\')
file_dir = base_dir + os.sep + "test" + os.sep + "test99.xlsx"
print(file_dir)

class test():
    def __init__(self,file_dir,sheet_name):
        self.rd = xlrd.open_workbook(file_dir)
        self.sh = self.rd.sheet_by_name(sheet_name)
        self.rows = self.sh.nrows
        self.cols = self.sh.ncols

    def ExcelRd(self):
        r = []
        for i in range(1,self.rows):
            values = self.sh.row_values(i,0,self.cols)
            r.append(values)
        return r

if __name__ == '__main__':
    #指定sheet页为：rdData
    file_dir = input("路径为：")
    sheet_name = input("sheet页为：")
    data = test(file_dir,sheet_name).ExcelRd()

    driver = webdriver.Chrome()
    driver.maximize_window()
    driver.implicitly_wait(10)
    driver.get("https://www.baidu.com")

    for footballStar in data:
        driver.find_element(By.CSS_SELECTOR,"#kw").clear()
        driver.find_element(By.CSS_SELECTOR,"#kw").send_keys(footballStar[1])
        driver.find_element(By.CSS_SELECTOR,"#su").click()
        sleep(5)

    driver.quit()

写法②：添加截图方法

function.py：

import os

def screenshot(driver,img_name):
    base = os.path.dirname(os.path.dirname(__file__))
    base_dir = base.replace("/","\\")
    img_dir = base_dir + os.sep + "20180515作业" + os.sep + "image" + os.sep + img_name + ".png"
    driver.get_screenshot_as_file(img_dir)

Excel读取数据.py：

import xlrd
import os
from selenium import webdriver
from selenium.webdriver.common.by import By
from time import sleep
from function import screenshot

class test(object):
    def __init__(self):
        self.base = os.path.dirname(os.path.dirname(__file__))
        self.base_dir = self.base.replace('/', '\\')

    def ExcelRd(self):
        file_dir = self.base_dir + os.sep + "20180515作业" + os.sep + "test_xlsx.xlsx"
        rd = xlrd.open_workbook(file_dir)
        sh = rd.sheet_by_name("rdData")
        rows = sh.nrows
        cols = sh.ncols

        r = []
        for i in range(1,rows):
            values = sh.row_values(i,0,cols)
            r.append(values)
        return r

if __name__ == '__main__':

    data = test().ExcelRd()
    driver = webdriver.Chrome()
    driver.maximize_window()
    driver.implicitly_wait(10)
    driver.get("https://www.baidu.com")

    for footballStar in data:
        fbStar = footballStar[1]
        driver.find_element(By.CSS_SELECTOR,"#kw").clear()
        driver.find_element(By.CSS_SELECTOR,"#kw").send_keys(fbStar)
        driver.find_element(By.CSS_SELECTOR,"#su").click()
        sleep(3)
        fbStar_xlsx = str("xlsx_" + fbStar)
        screenshot(driver,fbStar_xlsx)
        sleep(7)

    driver.quit()

二、从CSV读取数据进行百度搜索

CSV读取数据.py：

import csv
import os
from selenium import webdriver
from selenium.webdriver.common.by import By
from time import sleep
from function import screenshot

class test(object):
    def __init__(self):
        base = os.path.dirname(os.path.dirname(__file__))
        self.base_dir = base.replace("/","\\")

    def CSVRd(self):
        base_dir = self.base_dir + os.sep + "20180515作业" + os.sep + "test_csv.csv"
        opFile = open(base_dir,'r')
        rd = csv.reader(opFile)

        r = []
        next(rd,None)
        for i in rd:
            r.append(i)
        return r

if __name__ == '__main__':

    data = test().CSVRd()
    driver = webdriver.Chrome()
    driver.maximize_window()
    driver.get("https://www.baidu.com")
    driver.implicitly_wait(10)

    for fbStar in data:
        fbStar = fbStar[1]
        driver.find_element(By.CSS_SELECTOR,"#kw").clear()
        driver.find_element(By.CSS_SELECTOR,"#kw").send_keys(fbStar)
        driver.find_element(By.CSS_SELECTOR,"#su").click()
        sleep(3)
        csv_fbStar = str("csv_" + fbStar)
        screenshot(driver,csv_fbStar)
        sleep(7)

    driver.quit()

三、从XML读取数据进行登录操作

test_xml文件：

<?xml version="1.0" encoding="utf-8"?>
<info>
    <title>博客园登录</title>
    <url_dir>https://passport.cnblogs.com/user/signin</url_dir>
    <login username="owen_name" password="owen_pwd">登录</login>
</info>

CSV读取数据.py：

import xml.dom.minidom as minidom
# import xml.etree.ElementTree as ele
import os
from selenium import webdriver
from selenium.webdriver.common.by import By
from time import sleep
from function import screenshot

base = os.path.dirname(os.path.dirname(__file__))
base_dir = base.replace("/","\\")
file_dir = base_dir + os.sep + "20180515作业" + os.sep + "test_xml.xml"

#打开xml文档
dom = minidom.parse(file_dir)
#得到文档元素
root = dom.documentElement
#由于下面getElementsByTagName点不出来方法，手写的
tag1 = root.getElementsByTagName("login")
tag2 = root.getElementsByTagName("url_dir")
tag3 = root.getElementsByTagName("title")
#获得标签属性值
username = tag1[0].getAttribute("username")
password = tag1[0].getAttribute("password")
#获得标签之间的数据
url = tag2[0].firstChild.data
title = tag3[0].firstChild.data

driver = webdriver.Chrome()
driver.maximize_window()
driver.get(url)
driver.find_element(By.CSS_SELECTOR,"#input1").clear()
driver.find_element(By.CSS_SELECTOR,"#input1").send_keys(username)
sleep(3)
driver.find_element(By.CSS_SELECTOR,"#input2").clear()
driver.find_element(By.CSS_SELECTOR,"#input2").send_keys(password)
sleep(3)
title = str("xml_" + title)
screenshot(driver,title)

driver.quit()

四、附：学习资料

《Python不归路_xml.etree.ElementTree模块》感谢作者：深海一尾鱼

《python读取xml文件》感谢作者：虫师