本帖最后由 Hatsune_miku 于 2019-6-26 13:37 编辑
高考完了，是时候填志愿了，去哪里呢，去哪所大学呢，大学历年录取分数线多少呢？
我老弟(不是我)也遇到这样的问题，干脆写个脚本获取所有想去城市的大学的本科院校，来慢慢看。
软件介绍
获取高校的地址是：daxue.eol.cn，查询分数线的API是百度的。查询院校均为本科院校。
使用教程
安装依赖：
[Shell] 纯文本查看 复制代码 pip install requests lxml xlrd xlwt xlutils
目前获取的是【上海】【北京】【浙江】【广东】四个地方的本科学校：
分别对应getSchool函数里的alis：
[Python] 纯文本查看 复制代码 alis = ['sh', 'bj', 'zj', 'gd']
for city in alis:
if city == 'sh':
num = 39
if city == 'bj':
num = 69
if city == 'zj':
num = 59
if city == 'gd':
num = 67
alis列表里面的字母是每个城市or省的名称拼音缩写。sh=上海，bj=北京，以此类推，这里可以修改为自己想查的城市。
下面的num是一个城市所有的本科院校，可以打开：https://daxue.eol.cn/mingdan.shtml，然后找自己想查找的城市，进去之后看序号，到最后一个本科学校的序号是多少，这里就依次对应填多少。
myCity = '江西' # 你户口所在地(高考所在地)
mySubject = '理科' # 可选【文科】【理科】【综合】综合一般是新高考政策才会选，一般户口所在地为浙江或者上海或者别的地方。
如果想查211，985大学，把main函数里的schools = getSchool() 改成 schools = getProjectSchool()
运行截图：
运行完毕的时候，程序会在运行目录生成一个University.xls，这个就是我们获取到的数据啦。
Python运行版本：Python3
最后祝高三学子都能找到自己满意的大学。
完整代码：
[Python] 纯文本查看 复制代码 import requests
import xlrd
import xlwt
from xlutils.copy import copy
from lxml import etree
book_name_xls = 'University.xls'
sheet_name_xls = 'University'
def write_excel_xls(path, sheet_name, value):
index = len(value) # 获取需要写入数据的行数
workbook = xlwt.Workbook() # 新建一个工作簿
sheet = workbook.add_sheet(sheet_name) # 在工作簿中新建一个表格
for i in range(0, index):
for j in range(0, len(value[i])):
sheet.write(i, j, value[i][j]) # 像表格中写入数据（对应的行和列）
workbook.save(path) # 保存工作簿
print("xls格式表格写入数据成功！")
def write_excel_xls_append(path, value):
index = len(value) # 获取需要写入数据的行数
workbook = xlrd.open_workbook(path) # 打开工作簿
sheets = workbook.sheet_names() # 获取工作簿中的所有表格
worksheet = workbook.sheet_by_name(sheets[0]) # 获取工作簿中所有表格中的的第一个表格
rows_old = worksheet.nrows # 获取表格中已存在的数据的行数
new_workbook = copy(workbook) # 将xlrd对象拷贝转化为xlwt对象
new_worksheet = new_workbook.get_sheet(0) # 获取转化后工作簿中的第一个表格
for i in range(0, index):
for j in range(0, len(value[i])):
new_worksheet.write(i+rows_old, j, value[i][j]) # 追加写入数据，注意是从i+rows_old行开始写入
new_workbook.save(path) # 保存工作簿
print("xls格式表格【追加】写入数据成功！")
def read_excel_xls(path):
workbook = xlrd.open_workbook(path) # 打开工作簿
sheets = workbook.sheet_names() # 获取工作簿中的所有表格
worksheet = workbook.sheet_by_name(sheets[0]) # 获取工作簿中所有表格中的的第一个表格
for i in range(0, worksheet.nrows):
for j in range(0, worksheet.ncols):
print(worksheet.cell_value(i, j), "\t", end="") # 逐行逐列读取数据
print()
def getSchool():
alis = ['sh', 'bj', 'zj', 'gd']
for city in alis:
if city == 'sh':
num = 39
if city == 'bj':
num = 69
if city == 'zj':
num = 59
if city == 'gd':
num = 67
r = requests.get(f'http://daxue.eol.cn/{city}.shtml')
r.encoding='utf-8'
page = etree.HTML(r.text)
for i in range(num):
cengci_a = page.xpath(f'/html/body/div[3]/div[2]/div[2]/table/tbody/tr[{i+3}]/td[2]')
for cengci in cengci_a:
schools.append(cengci.text)
return schools
def getProjectSchool(): # 211 985
alis = ['211', '985']
for project in alis:
if project == '211':
num = 116 # 116所
x = 3
if project == '985':
num = 39
x = 2
r = requests.get(f'https://daxue.eol.cn/{project}.shtml')
r.encoding='utf-8'
page = etree.HTML(r.text)
for i in range(num):
tag_a = page.xpath(f'/html/body/div[3]/div[2]/div[{x}]/table/tbody/tr[{i+1}]/td[1]/a')
for a in tag_a:
schools.append(a.text)
tag_b = page.xpath(f'/html/body/div[3]/div[2]/div[{x}]/table/tbody/tr[{i+1}]/td[2]/a')
for b in tag_b:
schools.append(b.text)
return schools
def Query(school):
url = 'https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36'
}
params = {
'resource_id': '34559',
'query': school,
'co': f'tr[select1={myCity},select2={mySubject}]|th[select1={myCity},select2={mySubject}]',
'format': 'json',
'oe': 'utf-8',
'ie': 'utf-8',
'_': '1561384786050'
}
r = requests.get(url, params = params, headers = headers).json()
for i in range(len(r['data'][0]['tr'])):
year = r['data'][0]['tr'][i]['col'][0]['info'][0]['text']
average = r['data'][0]['tr'][i]['col'][1]['info'][0]['text']
low = r['data'][0]['tr'][i]['col'][2]['info'][0]['text']
shengkong = r['data'][0]['tr'][i]['col'][3]['info'][0]['text']
batch = r['data'][0]['tr'][i]['col'][4]['info'][0]['text']
value1 = [[year, average, low, shengkong, batch, school],]
write_excel_xls_append(book_name_xls, value1)
read_excel_xls(book_name_xls)
def main():
value_title = [["年份", "平均分", "最低分", "省控线", "批次", "学校"],]
write_excel_xls(book_name_xls, sheet_name_xls, value_title)
schools = getSchool()
for school in schools:
try:
Query(school)
except:
pass
if __name__ == '__main__':
schools = []
myCity = '江西'
mySubject = '理科'
main()
| 
[复制链接]
发表于 2019-6-26 09:18
