python爬取學校教務管理系統
阿新 • • 發佈:2018-12-02
寫這個爬蟲的緣由
以前用java寫過一個爬取學校的教務系統的爬蟲 https://blog.csdn.net/ygdxt/article/details/81158321,最近痴迷Python爬蟲,瞭解到許多強大的庫,想再一次用學校的教務系統做下測試。
這一次我首先想到的是新的教務系統,這個難度更大,因為有了驗證碼識別反爬,由於我是用的tessocr庫識別驗證碼,(具體配置過程可以參考我之前的部落格 python填坑之路:tesserocr配置)
用Requests.get方法把驗證碼下載下來識別之後,同時因為我爬取網頁是用的selenium做的模擬網頁動作,這裡就有一個同步性的問題,不能保證selenium請求網頁上的驗證碼和requests請求的驗證碼是同一個,相當於selenium、requests分別請求了一次登陸網頁,兩個網頁上的驗證碼顯然是不同的。所以
怎麼保證請求登入介面得到的網頁上的驗證碼
和我們請求驗證碼伺服器返回的驗證碼是同一個驗證碼是同一個是一個很迷人的問題,
我開始還以為可以從網頁原始碼上直接定位到這個驗證碼,結果顯示這個驗證碼在登入介面的
的存在形式不是一個..png/jpg,而是通過src=“驗證碼伺服器”來實現非同步載入
同時,由於tessocr識別驗證碼的成功率可能只有50%,要提高驗證率可能還要對接雲打碼,果斷放棄了爬取新教務系統的想法,還是爬取原來的沒有驗證碼的舊教務系統,
其實新舊教務系統最大的區別就是登陸介面不一樣,登陸之後都一樣,貌似用了重定向
ps:如果你對這個問題有什麼好的解決辦法,請不吝賜教
編碼過程
詳細的程式碼解釋就看註釋吧,有什麼問題歡迎交流
執行爬蟲的主程式csu.py
,裡面有許多測試用的註釋程式碼,就不刪了
from selenium import webdriver from selenium.webdriver.common.by import By from selenium.common.exceptions import TimeoutException from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.select import Select from config import * import time broswer = webdriver.Chrome() wait = WebDriverWait(broswer, 10) def search(): try: broswer.get("http://csujwc.its.csu.edu.cn/jsxsd/kscj/yscjcx_list") account = wait.until( EC.presence_of_element_located((By.CSS_SELECTOR, "#userAccount")) ) password = wait.until( EC.presence_of_element_located((By.CSS_SELECTOR, "#userPassword")) ) submit = wait.until( EC.element_to_be_clickable((By.CSS_SELECTOR, "#btnSubmit")) ) except TimeoutException: return search() #登入 account.send_keys(ACCOUNT) password.send_keys(PASSWORD) submit.click() #進入我的成績介面 my_score = wait.until( EC.presence_of_element_located((By.CSS_SELECTOR,"body > div.wap > a:nth-child(3) > div")) ) my_score.click() #成績和平均分 # my_rank = wait.until( # EC.presence_of_element_located((By.CSS_SELECTOR, "#LeftMenu1_divChildMenu > ul > li:nth-child(4) > a")) # ) # my_rank.click() # # rank = wait.until( # EC.presence_of_element_located((By.CSS_SELECTOR, "#dataList > tbody > tr:nth-child(2) > td:nth-child(3)")) # ) # #http://www.w3school.com.cn/cssref/selector_nth-child.asp nth-child(n)的用法 # average_score = wait.until( # EC.presence_of_element_located((By.CSS_SELECTOR, "#dataList > tbody > tr:nth-child(2) > td:nth-child(4)")) # ) # # print('您的平均成績是:'+average_score.text+"\n排名:"+rank.text) #逐次展示 我的成績八個子項 # css_selector = "#LeftMenu1_divChildMenu > ul > li:nth-child({0}) > a" # for i in range(8): # # 將滾動條移動到頁面的頂部 # js = "var q=document.documentElement.scrollTop=0" # broswer.execute_script(js) # time.sleep(2) # # aviable_score = wait.until( # EC.presence_of_element_located((By.CSS_SELECTOR, css_selector.format(str(i+1)))) # ) # aviable_score.click() # # # #將滾動條移動到頁面的底部 # for j in range(8): # js="var q=document.documentElement.scrollTop="+str(j*200) # broswer.execute_script(js) # time.sleep(1) #處理select https://www.cnblogs.com/imyalost/p/7846653.html yxcj = wait.until( EC.element_to_be_clickable((By.CSS_SELECTOR, "#LeftMenu1_divChildMenu > ul > li:nth-child(1) > a")) ) select_score_element = broswer.find_element_by_css_selector("#xnxq01id") select_score = Select(select_score_element) #得到下拉列表的所有子項 select_score_items = broswer.find_elements_by_css_selector("#xnxq01id option") select_score_items_text = [] for item in select_score_items: select_score_items_text.append(item.text) #print(item.text) scores_dic = {} for i in range(len(select_score.options)): #不加這兩行會報錯,原因: https://blog.csdn.net/ulebo/article/details/52128033 print("*****************************************************"+select_score_items_text[i]+ "*****************************************************") select_score_element = broswer.find_element_by_css_selector("#xnxq01id") select_score = Select(select_score_element) select_score.select_by_index(i) time.sleep(1) score_table = broswer.find_element_by_css_selector("#dataList") data = score_table.text.replace("+","") data = data.split("\n") datalist = [] for line in data: datalist.append(line.split()) scores_dic[select_score_items_text[i]] = datalist return scores_dic[select_score_items_text[0]] def main(): search() if __name__ =="__main__": main()
ui.py
程式的gui,直接執行這個就好,它會呼叫csu.py
#coding=utf-8
import wx
import wx.grid
import csu
class UI(wx.Frame):
def __init__(self):
wx.Frame.__init__(self,parent=None,title="成績查詢",size=(1050,560))
grid = wx.grid.Grid(self,pos=(10,0),size=(1050,500))
grid.CreateGrid(100,9)
for i in range(100):
for j in range(9):
grid.SetCellAlignment(i,j,wx.ALIGN_CENTER,wx.ALIGN_CENTER)
grid.SetColLabelValue(0, "序號") #第一列標籤
grid.SetColLabelValue(1, "初修學期")
grid.SetColLabelValue(2, "獲得學期")
grid.SetColLabelValue(3, "課程")
grid.SetColLabelValue(4, "成績") # 第一列標籤
grid.SetColLabelValue(5, "學分")
grid.SetColLabelValue(6, "課程屬性")
grid.SetColLabelValue(7, "課程性質")
grid.SetColLabelValue(8, "獲得方式") # 第一列標籤
grid.SetColSize(0,50)
grid.SetColSize(1,100)
grid.SetColSize(2,100)
grid.SetColSize(3,350)
grid.SetColSize(4,50)
grid.SetColSize(5,50)
grid.SetColSize(6,50)
grid.SetColSize(7,100)
grid.SetColSize(8,100)
grid.SetCellTextColour("NAVY")
data = csu.search()
data.remove(data[0])
print(data)
for i,item1 in enumerate(data):
for j,item2 in enumerate(item1):
grid.SetCellValue(i,j,data[i][j])
pass
app = wx.App()
frame = UI()
frame.Show()
app.MainLoop()