高分课程设计-基于python+flask+echarts 的大数据分析与可视化，可视化大屏，地图可视化，数据分析+源码+文档说

import csv import os.path import time from selenium import webdriver from selenium.webdriver.support.select import Select def save_province_name(): driver.get("https://yz.chsi.com.cn/zsml/queryAction.do") province = driver.find_element_by_id("ssdm") # 省市 province_list = Select(province) for option in province_list.options: province_name.append(option.text) def find_data(s): for zhuanye_num in range(1, 14): # 遍历13个专业 driver.get("https://yz.chsi.com.cn/zsml/queryAction.do") province = driver.find_element_by_id("ssdm") # 省市 Select(province).select_by_index(s) menlei = driver.find_element_by_id("mldm") # 门类/专业学位 Select(menlei).select_by_index(1) zyly = driver.find_element_by_id("yjxkdm") # 专业领域/(21/0854)电子信息 Select(zyly).select_by_index(21) zuanye = driver.find_element_by_id("zymc") # 13个专业 Select(zuanye).select_by_index(zhuanye_num) xxfs = driver.find_element_by_name("xxfs") # 学习方式：全日制 Select(xxfs).select_by_index(1) driver.find_element_by_name('button').click() # 查询按钮 school_urls = driver.find_elements_by_xpath( '//*[@id="form3"]/a') # 学校链接 school_url = [] for i in school_urls: school_url.append(i.get_attribute('href')) # print('school_url:\n', len(school_url)) for n in range(0, len(school_url)): # time.sleep(6) driver.get(school_url[n]) # 进入学校各学院 colleges = driver.find_elements_by_xpath( '/html/body/div[2]/div[3]/div/div[2]/table/tbody/tr') # 一个学校的所有学院 each_college(colleges) # 循环每个学院 save_data() # 保存一个专业的所有学校 # time.sleep(2) list_clear() # driver.quit() def each_college(colleges): # 循环每个学院 for each in range(1, len(colleges)+1): str_each = str(each) # time.sleep(6) driver.find_element_by_xpath( '/html/body/div[2]/div[3]/div/div[2]/table/tbody/tr['+str_each+']/td[8]/a').click() # 进入详细页面 windows = driver.window_handles data_details(windows) def list_clear(): school_name.clear() test_methd.clear() yuanxi.clear() zy.clear() research.clear() teacher.clear() students.clear() notes.clear() examinations.clear() def data_details(windows): # 获取详细页面数据 driver.switch_to.window(windows[1]) school_name.append(driver.find_element_by_xpath( './/table/tbody/tr[1]/td[2]').text) test_methd.append(driver.find_element_by_xpath( './/table/tbody/tr[1]/td[4]').text) yuanxi.append(driver.find_element_by_xpath( './/table/tbody/tr[2]/td[2]').text) zy.append(driver.find_element_by_xpath('.//table/tbody/tr[2]/td[4]').text) research.append(driver.find_element_by_xpath( './/table/tbody/tr[3]/td[4]').text) teacher.append(driver.find_element_by_xpath( './/table/tbody/tr[4]/td[2]').text) students.append(driver.find_element_by_xpath( './/table/tbody/tr[4]/td[4]').text) notes.append(driver.find_element_by_xpath( './/table/tbody/tr[5]/td[2]').text) obj1 = driver.find_element_by_xpath( '/html/body/div[2]/div[3]/div[1]/div[1]/div/table/tbody/tr/td[1]').text obj2 = driver.find_element_by_xpath( '/html/body/div[2]/div[3]/div[1]/div[1]/div/table/tbody/tr/td[2]').text obj3 = driver.find_element_by_xpath( '/html/body/div[2]/div[3]/div[1]/div[1]/div/table/tbody/tr/td[3]').text obj4 = driver.find_element_by_xpath( '/html/body/div[2]/div[3]/div[1]/div[1]/div/table/tbody/tr/td[4]').text examinations.append(obj1.split( "\n")[0]+obj2.split("\n")[0]+obj3.split("\n")[0]+obj4.split("\n")[0]) driver.switch_to.window(windows[1]) driver.close() driver.switch_to.window(windows[0]) def save_data(): if(len(zy) != 0): with open(os.path.join(path_csv, csv_name), 'a', newline='') as f: csv_write = csv.writer(f) csv_write.writerow([f'{zy[0]}']) csv_write.writerow( ['招生单位', '院系所', '专业', '研究方向', '考试方式', '考试科目', '招录人数', '指导老师', '备注']) for i in range(0, len(zy)): print("招生单位:", school_name[i]) print("院系所:", yuanxi[i]) print("专业:", zy[i]) print("研究方向:", research[i]) print("考试方式:", test_methd[i]) print("考试科目:", examinations[i]) print("招录人数:", students[i].split( "：")[1].split("(")[0]) print("指导老师:", teacher[i]) print("备注:", notes[i]) with open(os.path.join(path_csv, csv_name), 'a', newline='') as f: csv_write = csv.writer(f) # csv_write.writerow([zy[i]]) csv_write.writerow([school_name[i], yuanxi[i], zy[i], research[i], test_methd[i], examinations[i], students[i].split( "：")[1].split("(")[0], teacher[i], notes[i]]) # f.close() if __name__ == '__main__': option = webdriver.ChromeOptions() option.add_argument('headless') driver = webdriver.Chrome(options=option) # 浏览器驱动,不打开浏览器运行 # driver = webdriver.Chrome() # 打开浏览器 province_name = [] # 省/市名 school_name = [] # 学校名 test_methd = [] # 考试方式 yuanxi = [] # 院系 zy = [] # 专业 research = [] # 研究方向 teacher = [] # 指导老师 students = [] # 招收人数 notes = [] # 备注 examinations = [] # 考试科目 save_province_name() # 保存省名 path_csv = r"D:\桌面\考研大数据\数据分析\data" # 保存路径 csv_name = '' # 文件名 for s in range(1, 32): # 遍历31个省份 page = 0 csv_name = f'{province_name[s]}.csv' # 保存文件名称 find_data(s)