python爬虫小作业

需求如下：
       爬取菜鸟教程的PHP测题"https://www.runoob.com/quiz/php-quiz.html"。
       爬取测验题中的题目、选项、答案、答案解析。
       将爬取内容分别存入word文件中，并将所有word文件打包成压缩文件。

代码如下：

from selenium import webdriver
from docx import document
from docx.shared import Pt
import zipfile
import os
import shutil

# 文件名
file='PHP测验题'
# 创建文件夹
os.mkdir(file)
# 压缩文件夹函数  src_dir:要压缩的文件夹的路径;  zip_name：压缩后zip文件的路径及名称
def zip_file(src_dir):
    zip_name = src_dir +'.zip'
    z = zipfile.ZipFile(zip_name,'w',zipfile.ZIP_DEFLATED)
    for dirpath, dirnames, filenames in os.walk(src_dir):
        fpath = dirpath.replace(src_dir,'')
        fpath = fpath and fpath + os.sep or ''
        for filename in filenames:
            z.write(os.path.join(dirpath, filename),fpath+filename)
    z.close()

path = 'chromedriver.exe'
browser = webdriver.Chrome(path)

url1 = 'https://c.runoob.com/quiz/5550/'
url2 = 'https://c.runoob.com/quiz/5551/'
url3 = 'https://c.runoob.com/quiz/5553/'
url4 = 'https://c.runoob.com/quiz/5554/'
url5 = 'https://c.runoob.com/quiz/5555/'
url6 = 'https://c.runoob.com/quiz/5556/'
url7 = 'https://c.runoob.com/quiz/5557/'
url8 = 'https://c.runoob.com/quiz/5559/'
url9 = 'https://c.runoob.com/quiz/5560/'
url10 = 'https://c.runoob.com/quiz/5561/'
url11 = 'https://c.runoob.com/quiz/5562/'
url12 = 'https://c.runoob.com/quiz/5563/'
url13 = 'https://c.runoob.com/quiz/5564/'
url14 = 'https://c.runoob.com/quiz/5565/'
url15 = 'https://c.runoob.com/quiz/5566/'

# 网址
url = [url1,url2,url3,url4,url5,url6,url7,url8,url9,url10,url11,url12,url13,url14,url15]

# 打开网站
for k in range(len(url)):
    # 创建document对象
    document = document()
    # 打开网站
    browser.get(url[k])

    # 获取测试题题目
    problem = browser.find_element_by_tag_name('h4')
    # 打印标题
    # document.add_heading(problem.text+"n")
    # 获取题目按钮
    button1 = browser.find_elements_by_css_selector('div[] > ol > li')
    # 获取“检查”按钮
    button = browser.find_elements_by_name('check')
    # 获取问题
    question = browser.find_elements_by_css_selector('div[]')
    # 获取选项
    option = browser.find_elements_by_css_selector('li[] label')
    # 获取abcd
    option1 = browser.find_elements_by_css_selector('li[]')
    # 获取答案解析
    exp = browser.find_elements_by_css_selector('div[]')

    a=0
    list1 = []
    Li = browser.find_elements_by_class_name("wpProQuiz_listItem")
    for i in range(len(Li)):
        li = Li[i].find_elements_by_css_selector('ul[data-question_id] > li')
        list1.append(len(li))

    for i in range(len(button1)):
        # 点击所有题目的检查按钮，把答案显露出来
        # 网上找的办法（Selenium无法点击元素，报错：ElementClickInterceptedException:element click intercepted）   "https://www.cnblogs.com/xiaoguo-/p/12143912.html"
        browser.execute_script("arguments[0].click();", button1[i])
        # button1[i].click()    点击按钮
        browser.execute_script("arguments[0].click();", button[i])
        # button[i].click()
        ans = browser.find_elements_by_css_selector('li[]')
        # 打印问题和代码
        document.add_paragraph(str(i+1)+".【单选题】" + question[i].text + "（   ）n")

        # 打印选项
        for j in range(list1[i]):
           document.add_paragraph(chr(int(option1[a].get_attribute('data-pos'))+65)+"."+option[a].text+"n")
           a+=1

        # 打印答案
        document.add_paragraph("答案："+chr(int(ans[i].get_attribute('data-pos'))+65) + "n")

        #打印答案解析
        document.add_paragraph("答案解析：" + exp[i].text + "nn")

        #调整行间距/段后间距/段前间距
        for paragraph in document.paragraphs:
            paragraph.paragraph_format.line_spacing = 1
            paragraph.paragraph_format.space_before = Pt(0)
            paragraph.paragraph_format.space_after = Pt(0)
        document.save( file + '/' + problem.text +'.docx')

# 压缩文件夹
zip_file(file)
# 删除文件夹
shutil.rmtree(file)
browser.close()