# 繞過驗(yàn)證碼無限次獲取上學(xué)吧題目答案
# 上學(xué)吧網(wǎng)址：https://www.shangxueba.com/ask
import os
import random
import requests
import urllib3
urllib3.disable_warnings() # 這句和上面一句是為了忽略 https 安全驗(yàn)證警告，參考：https://www.cnblogs.com/ljfight/p/9577783.html
from bs4 import BeautifulSoup
from PIL import Image
def get_verifynum(session): # 網(wǎng)址的驗(yàn)證碼邏輯是先去這個(gè)網(wǎng)址獲取驗(yàn)證碼圖片，提交計(jì)算結(jié)果到另外一個(gè)網(wǎng)址進(jìn)行驗(yàn)證。
r = session.get("https://www.shangxueba.com/ask/VerifyCode2.aspx", verify=False) # HTTPS 請(qǐng)求進(jìn)行 SSL 驗(yàn)證或忽略 SSL 驗(yàn)證才能請(qǐng)求成功，忽略方式為 verify=False。參考：https://www.cnblogs.com/ljfight/p/9577783.html
with open('temp.png','wb+') as f:
f.write(r.content)
image = Image.open('temp.png')
image.show() # 調(diào)用系統(tǒng)的圖片查看軟件打開驗(yàn)證碼圖片，如果不能打開，可以自己找到 temp.png 打開。
verifynum = input("\n請(qǐng)輸入驗(yàn)證碼圖片中的計(jì)算結(jié)果：")
image.close()
os.remove("temp.png")
return verifynum
def get_question(session):
r = session.get(link)
soup = BeautifulSoup(r.content, "html.parser")
description = soup.find(attrs={"name":"description"})['content'] # 抓取題干內(nèi)容
return description
def get_answer(session, verifynum, dataid):
data1 = {
"Verify": verifynum,
"action": "CheckVerify",
}
session.post("https://www.shangxueba.com/ask/ajax/GetZuiJia.aspx", data=data1) # 核查驗(yàn)證碼正確性
data2 = {
"phone":"",
"dataid": dataid,
"action": "submitVerify",
"siteid": "1001",
"Verify": verifynum,
}
r = session.post("https://www.shangxueba.com/ask/ajax/GetZuiJia.aspx", data=data2)
soup = BeautifulSoup(r.content, "html.parser")
ans = soup.find('h6')
print("\n" + '-'*45)
if(ans): # 只有驗(yàn)證碼核查通過才會(huì)顯示答案
print("\n題目：" + get_question(session))
print(ans.text)
else:
print('\n沒有找到答案！請(qǐng)檢查驗(yàn)證碼或網(wǎng)址是否輸入有誤！\n')
print('-'*45)
if __name__ == '__main__':
s = requests.session()
while True:
s.headers.update({"X-Forwarded-For":"%d.%d.%d.%d"%(random.randint(120,125),random.randint(1,200),random.randint(1,200),random.randint(1,200))}) # 這一句是整個(gè)程序的關(guān)鍵，通過修改 X-Forwarded-For 信息來欺騙 ASP 站點(diǎn)對(duì)于 IP 的驗(yàn)證。
link = input("\n請(qǐng)輸入上學(xué)吧網(wǎng)站上某道題目的網(wǎng)址，例如：https://www.shangxueba.com/ask/8952241.html\n\n請(qǐng)輸入：").strip() # 過濾首尾的空格
if(link[0:31] != "https://www.shangxueba.com/ask/" or link[-4:] != "html"):
print("\n網(wǎng)址輸入有誤！請(qǐng)重新輸入！\n")
continue
dataid = link.split("/")[-1].replace(r".html","") # 提取網(wǎng)址最后的數(shù)字部分
if(dataid.isdigit()): # 根據(jù)格式，dataid 應(yīng)該全部為數(shù)字，判斷字符串是否全部為數(shù)字，返回 True 或者 False
verifynum = get_verifynum(s)
get_answer(s, verifynum, dataid)
else:
print("\n網(wǎng)址輸入有誤！請(qǐng)重新輸入！\n")
continue