python|网页自动填写 selenium|爬虫

网页自动填写

前言
效果
使用教程
文件下载
源码

前言最近看学弟在写视听说的网课，想起来我在当时懒得一个一个填，就写了一个自动填写的程序。学校这个网站的题目应该不会更新，所以应该能一届一届用下去吧2333
效果
使用教程本程序借助的是python的selenium库调用chrome进行操作，所以需要一个谷歌官方提供的api接口，就是这个chromedriver，每个版本的chrome需要使用对应的chromedriver，将chromedriver这个文件夹里面的文件替换就好了。

文章图片
这里可以查看chrome的版本

文章图片

运行里面这个视听说.exe输入账号密码单元就能开始自动填写了。

文章图片

文件下载链接：https://pan.baidu.com/s/1poQXcnFmDPOjufrpdVwLMg
提取码：x274
这里面除了视听说，还有大二下学期的工程英语视听说，操作方法是一样的。
源码网页填写代码

from selenium import webdriver from extract_answer import * from retrying import retry import time import re__author__ = 'ghost222'class shitingshuo(): def __init__(self, account, password): # self.answer=extract_answer(unit) self.driver = webdriver.Chrome('./chromedriver/chromedriver.exe') self.account = account self.password = password # self.unit=unitdef preparation(self): self.driver.get('http://202.119.161.130/common/index.aspx') try: self.driver.find_element_by_id('ctl00_ContentPlaceHolder1_UcLogin1_txt_UserName')\ .send_keys(self.account) self.driver.find_element_by_id('ctl00_ContentPlaceHolder1_UcLogin1_txt_PassWord')\ .send_keys(self.password) self.driver.find_element_by_id('ctl00_ContentPlaceHolder1_UcLogin1_ibtn_ok')\ .click() except: self.driver.get( 'http://202.119.161.130/CourseLearning/ClassroomOnline.aspx') self.driver.find_element_by_xpath('//*[@id="ctl00_ContentPlaceHolder1_div_ok"]/table/tbody/tr[5]/td/table/tbody/tr[2]/td[3]/a')\ .click() self.select_unit() self.driver.find_element_by_link_text('Task 1').click()def select_unit(self): temp_unit_xpath = '//*[@id="aspnetForm"]/table/tbody/tr/td[2]/table[1]/tbody/tr[3]/td/div/span/table/tbody/tr[{0}]/td[{1}]/a' unit_xpath = temp_unit_xpath.format( (self.unit+1)//2, ((self.unit+1) % 2+1)*2) self.driver.find_element_by_xpath(unit_xpath).click()@retry(stop_max_attempt_number=4)# 重复尝试 def do_task1(self): ans = self.answer.task1() #try: for a in ans: self.driver.find_element_by_name(ans.index(a)).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() # except:# 跳过非做题页 #self.driver.find_element_by_link_text('Next').click() #raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task2(self): ans = self.answer.task2() try: for a in ans: self.driver.find_element_by_name(ans.index(a)).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task3(self): ans = self.answer.task3() try: for a in ans: self.driver.find_element_by_name(ans.index(a)).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task4(self): ans = self.answer.task4() try: for a in ans: self.driver.find_element_by_name(ans.index(a)).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task5(self): ans = self.answer.task5() try: self.driver.find_element_by_xpath( '//*[@id="div1"]/div/table/tbody/tr[3]/td/table/tbody/tr/td[2]/table/tbody/tr[2]/td/textarea').send_keys(ans[0]) self.driver.find_element_by_xpath( '//*[@id="div1"]/div/table/tbody/tr[3]/td/table/tbody/tr/td[2]/table/tbody/tr[4]/td/textarea').send_keys(ans[0]) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task6(self): try: ans = self.answer.task6() for a in ans: temp_xpath = '//*[@id="div1"]/div/table/tbody/tr[3]/td/table/tbody/tr/td[2]/table/tbody/tr[{}]/td/textarea'.format( (ans.index(a)+1)*2) self.driver.find_element_by_xpath(temp_xpath).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() try: a1 = self.driver.switch_to.alert a1.accept() finally: pass self.driver.find_element_by_link_text('Next').click() except Exception: self.driver.find_element_by_link_text('Next').click()@retry(stop_max_attempt_number=1)# 重复尝试 def do_task7(self): try: ans = self.answer.task7() for a in ans: self.driver.find_element_by_name(ans.index(a)).send_keys(a) self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() time.sleep(5)# 赞停5秒，防止服务器检测 try: a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task8(self): ans = self.answer.task8() try: for a in ans: self.driver.find_element_by_name(ans.index(a)).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task9(self): ans = self.answer.task9() try: for a in ans: temp_xpath = '//*[@id="div1"]/div/table/tbody/tr[3]/td/table/tbody/tr/td[2]/table/tbody/tr//*[@value=https://www.it610.com/"{}\"]'.format( a) self.driver.find_element_by_xpath(temp_xpath).click() time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task10(self): ans = self.answer.task10() count = 0 temp_xpath = '//*[@id="div1"]/div/table/tbody/tr[3]/td/table/tbody/tr/td[2]/table/tbody/tr[{}]/td/input' index = {'A': 2, 'B': 3, 'C': 4, 'D': 5} try: for a in ans: xpath = temp_xpath.format(index[a]+5*count) self.driver.find_element_by_xpath(xpath).click() count += 1 time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task11(self): ans = self.answer.task11() try: for a in ans: temp_xpath = '//*[@id="div1"]/div/table/tbody/tr[3]/td/table/tbody/tr/td[2]/table/tbody/tr[{}]/td/textarea'.format( (ans.index(a)+1)*2) self.driver.find_element_by_xpath(temp_xpath).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task14(self): ans = self.answer.task14() try: for a in ans: self.driver.find_element_by_name(ans.index(a)).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass finally: self.driver.find_element_by_link_text('Next').click() except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()@retry(stop_max_attempt_number=3)# 重复尝试 def do_task15(self): ans = self.answer.task15() try: for a in ans: self.driver.find_element_by_name(ans.index(a)).send_keys(a) time.sleep(5)# 赞停5秒，防止服务器检测 try: self.driver.find_element_by_name( 'ctl00$ContentPlaceHolder1$submit').click() a1 = self.driver.switch_to.alert a1.accept() except:# 跳过已做的Task pass except:# 跳过非做题页 self.driver.find_element_by_link_text('Next').click() raise Exception()def run(self, unit): self.answer = extract_answer(unit) self.unit = unit self.preparation() # for num in range(3): #self.driver.find_element_by_link_text('Next').click() self.do_task1() self.do_task2() self.do_task3() self.do_task4() self.do_task5() self.do_task6() self.do_task7() self.do_task8() self.do_task9() self.do_task10() self.do_task11() self.do_task14() self.do_task15()if __name__ == '__main__': account = input('输入账号：') password = input('输入密码：') units = input('输入单元(用逗号隔开，如：1,2,3)：') units = [int(i) for i in units.split(',')] sts = shitingshuo(account, password) for i in units: sts.run(i)

【python|网页自动填写】从txt中提取答案的代码，利用正则表达式提取的。

import re import sys import os # os.chdir(sys.path[0])class extract_answer(): def __init__(self, unit): self.unit = unit self.file = open('.\视听说答案.txt', 'r', encoding='utf-8') self.content = self.search_unit(unit)def search_unit(self, unit): if unit > 10 or unit < 1: raise Exception('无效unit') while True: line = self.file.readline() if 'U'+str(unit) in line: break content = self.file.read() if unit == 10: total_content = re.search('Task 1(.+)', content, re.S).group(0) elif unit > 0 and unit < 10: total_content = re.search( 'Task 1(.+?)'+'U'+str(unit+1), content, re.S).group(0) return total_contentdef task1(self): content = re.search('Task 1(.+?)Task 2', self.content, re.S).group() answer = re.findall('$\s*(\w+?)\s*$ \[', content, re.S) if not answer: raise Exception('task1未找到答案') return answerdef task2(self): content = re.search('Task 2(.+?)Task 3', self.content, re.S).group() answer = re.findall('$(.+?)$', content, re.S) if not answer: raise Exception('task2未找到答案') return answerdef task3(self): content = re.search('Task 3(.+?)Task 4', self.content, re.S).group() answer = re.findall('$(.+?)$', content, re.S) if not answer: raise Exception('task3未找到答案') return answerdef task4(self): content = re.search('Task 4(.+?)Task 5', self.content, re.S).group() answer = re.findall('\)\s*$(.+?)$', content, re.S) if not answer: raise Exception('task4未找到答案') return answerdef task5(self): content = re.search('Task 5(.+?)Task 6', self.content, re.S).group() answer = re.findall('Reference answer： (.+?)\.', content, re.S) if not answer: raise Exception('task5未找到答案') return answerdef task6(self): content = re.search('Task 6(.+?)Task 7', self.content, re.S).group() answer = re.findall('Reference answer：[\s]*(.+?)\.', content, re.S) if not answer: raise Exception('task6未找到答案') return answerdef task7(self): content = re.search('Task 7(.+?)Task 8', self.content, re.S).group() answer = re.findall('\)$(.+?)$', content, re.S) if not answer: raise Exception('task7未找到答案') return answerdef task8(self): content = re.search('Task 9(.+?)Task 9', self.content, re.S).group() answer = re.findall('$(.+?)$', content, re.S) if not answer: raise Exception('task8未找到答案') return answerdef task9(self): content = re.search('Task 9(.+?)Task 9(.+?)Task 10', self.content, re.S).group(2) answer = re.findall('$(.+?)$', content, re.S) if not answer: raise Exception('task9未找到答案') return answerdef task10(self): content = re.search('Task 10(.+?)Task 11', self.content, re.S).group() answer = re.findall('[\.|\?][\s]*$(.+?)$', content, re.S) if not answer: raise Exception('task10未找到答案') return answerdef task11(self): content = re.search('Task 11(.+?)Task (12|14)', self.content, re.S).group() answer = re.findall('Reference answer： (.+?)\.', content, re.S) if not answer: raise Exception('task11未找到答案') return answerdef task14(self): content = re.search('Task 14(.+?)Task 15', self.content, re.S).group() answer = re.findall('$(.+?)$', content, re.S) if not answer: raise Exception('task14未找到答案') return answerdef task15(self): content = re.search('Task 15(.+)', self.content, re.S).group() answer = re.findall('\)$(.+?)$', content, re.S) if not answer: raise Exception('task15未找到答案') return answerif __name__ == '__main__': a = extract_answer(9) b = a.task8() print(b, len(b))