python 抓取下拉列表控制的表格的所有数据

import re
from selenium import webdriver

f = open("HunanTest.txt",‘r‘,encoding="utf-8")  # 打开抓取的url文件
univs = []
for i in f:  # 用正则表达式匹配数字（学校id）存在univs列表中
    univid = re.search(r‘d+‘,i).group()
    univs.append(univid)

browser = webdriver.Firefox()
info = []
vacant = []

# 四重for循环用于构建新的Url
for univ in univs:
    for provId in open("prov.txt",encoding=‘utf-8‘):  # 各省份的id
        for typeId in range(1,3):  # 类别，理科是1，文科是2
            for year in range(2016,2019):  # 年份，2016-2018
                url = "https://api.eol.cn/gkcx/api/?access_token=&local_province_id=" + str(
                    provId) + "&local_type_id="                       + str(typeId) + "&school_id=" + str(univ) + "&signsafe=&uri=apidata/api/gk/score/province&year="                       + str(year)
                browser.get(url)
                html = browser.page_source
                # 正则表达式匹配相关信息
                try:
                    name = re.findall(r‘"name":"(.+?)",‘,html)
                    prov = re.findall(r‘"local_province_name":"(.+?)",html)
                    typeNum = re.findall(r‘"local_type_name":"(.+?)",html)
                    average = re.findall(r‘"average":"(.+?)",html)
                    min = re.findall(r‘"min":"(.+?)",html)
                    max = re.findall(r‘"max":"(.+?)",html)
                    proscore = re.findall(r‘"proscore":"(.+?)",html)
                    batch = re.findall(r‘"local_batch_name":"(.+?)",html)
                    # 构建数据字典
                    data = {"学校名称": name[0],"学校ID": univ,"省份": prov[0],"年份": year,"类别": typeNum[0],"平均分": average[0],"最高分": max[0],"最低分": min[0],"省份批次线": proscore[0],"录取批次": batch[0]
                            }
                    print(data)
                    info.append(data)
                # 异常处理，很多学校在部分省份的招生信息是缺失的，获取不到信息时，就打印url并存储（暂无他用）
                except IndexError:
                    print(url)
                    vacant.append(url)

browser.close()