每周分享【一】 用Python爬取天津大学课程表
2019-03-13 本文已影响0人
LinoX
需要的库
import time
import bs4
import xlwt #用来写入Excel
from selenium import webdriver #模拟浏览器行为
from bs4 import BeautifulSoup
import getpass #隐藏输入的密码
# 还要单独安装chromedriver
思路:
由于校园办公网的课程表页是用js渲染出来的而不是静态页面,所以不直接用requests库去get页面,那样得到的网页源代码是不经js渲染的,而校园网又没有提供接口,所以只能暴力解决。Selenium神器登场
- 定位登录页面元素
- 自动登录
- 自动进入课程表页
- 获取渲染后的网页源代码
- BeautifulSoup解析
- 写入数据
上代码
import time
import bs4
import xlwt
from selenium import webdriver
from bs4 import BeautifulSoup
import getpass
#获取渲染后的代码
browser = webdriver.Chrome()
url = "http://classes.tju.edu.cn"
username = input("学号:")
password = getpass.getpass("密码:")
browser.get(url)
time.sleep(2)
browser.find_element_by_name('username').send_keys(username)
time.sleep(2)
browser.find_element_by_name('password').send_keys(password)
time.sleep(2)
browser.find_element_by_name('submit').click()
time.sleep(3)
browser.switch_to.frame('iframeMain')
browser.find_element_by_xpath("//div[@class='inner-list-2']/a[@href='/eams/courseTableForStd.action']").click()
time.sleep(3)
html = browser.page_source
#定位课程表
soup = BeautifulSoup(html, 'lxml')
# print(soup)
table = soup.find('table', attrs={'id': 'manualArrangeCourseTable'})
trs = table.find_all('tr')[1:]
# tds = trs[2].find_all('td')
# print(tds[1].text)
# 读入课程表
data = {
'0': [],
'1': [],
'2': [],
'3': [],
'4': [],
'5': [],
}
for i in range(0, 12):
if i % 2 != 0:
continue
if isinstance(trs[i], bs4.element.Tag):
tds = trs[i].find_all('td')
for j in range(1, 8):
a = str(int(i/2))
# print(a)
data[a].append(tds[j].text)
# print(data)
browser.close()
# 初始化表格
workbook = xlwt.Workbook(encoding='utf-8')
worksheet = workbook.add_sheet('课程表')
worksheet.col(0).width = 4000
for i in range(1, 6):
worksheet.col(i).width = 8000
style = xlwt.XFStyle()
font = xlwt.Font()
font.name = "宋体"
font.height = 13 * 20
alignment = xlwt.Alignment()
alignment.horz = xlwt.Alignment.HORZ_CENTER
alignment.vert = xlwt.Alignment.VERT_CENTER
style.font = font
style.alignment = alignment
worksheet.write(0, 0, "节次", style)
for i in range(1, 8):
a = str(i)
worksheet.write(0, i, "星期" + a, style)
for j in range(1, 6):
b = str(j)
c = str(2 * j)
worksheet.write(j, 0, "第" + b + "节" + '\n' + "第" + c + "节", style)
for i in range(1, 6):
for j in range(1, 8):
worksheet.write(i, j, data[str(i-1)][j-1], style)
workbook.save('课程表.xls')