<爬蟲>驗證碼登陸三種方式

1、手動輸入

 1 import requests
 2 from bs4 import BeautifulSoup
 3 
 4 '''手動輸入驗證碼：用瀏覽器登陸古詩文網，抓包獲取登陸接口和form表單；
 5                    將驗證碼圖片下載，輸入驗證碼，加入form表單；
 6                    獲取form表單所需參數；
 7                    帶着form表單發送登陸請求
 8                    注：須要創建會話'''
 9 
10 headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) '
11                          'AppleWebKit/537.36 (KHTML, like Gecko) '
12                          'Chrome/73.0.3683.86 Safari/537.36'}
13 
14 def download_code(s):
15     #向登陸界面發送請求
16     url = 'https://so.gushiwen.org/user/login.aspx?from='
17     r = s.get(url,headers=headers)
18 
19     #解析獲取驗證碼圖片連接
20     soup = BeautifulSoup(r.text,'lxml')
21     img_src = soup.find('img',id='imgCode')['src']
22     img_url = 'https://so.gushiwen.org' + img_src
23     print(img_url)
24 
25     #向圖片連接發送請求，下載圖片
26     r_img = s.get(img_url,headers=headers)
27     with open('img/code.png','wb') as fp:
28         fp.write(r_img.content)
29 
30     #查找form表單所需的兩個參數
31     __VIEWSTATE = soup.find('input',id='__VIEWSTATE')['value']
32     __VIEWSTATEGENERATOR = soup.find('input',id='__VIEWSTATEGENERATOR')['value']
33 
34     return __VIEWSTATE,__VIEWSTATEGENERATOR
35 
36 def login(s,VIEW,VIEWG):
37     post_url = 'https://so.gushiwen.org/user/login.aspx?from='
38 
39     code = input('輸入驗證碼：')
40 
41     form_data = {'__VIEWSTATE':VIEW,
42                 '__VIEWSTATEGENERATOR': VIEWG,
43                 'code':code,
44                 'denglu':'登陸',
45                 'email':'18404904721',
46                 'from':'',
47                 'pwd':'gjp625262'}
48 
49     r = s.post(url=post_url,headers=headers,data=form_data)
50 
51     with open('gushi.html','w',encoding='utf8') as fp:
52         fp.write(r.text)
53 
54 def main():
55     #建立會話
56     s = requests.Session()
57 
58     #下載驗證碼
59     VIEW,VIEWG = download_code(s)
60 
61     #進行登陸
62     login(s,VIEW,VIEWG)
63 
64 
65 if __name__ == '__main__':
66     main()

2、tesseract光學識別

from PIL import Image
import pytesseract

'''下載tesseract
    pip install pytesseract'''

#打開圖片
img = Image.open(r'img/code.png')

#轉化爲灰度圖片
img = img.convert('L')

#二值化處理
threshold = 140
table = []
for i in range(256):
    if i < threshold:
        table.append(0)
    else:
        table.append(1)
out = img.point(table,'1')
out.show()
img = img.convert('RGB')

#識別圖片
print(pytesseract.image_to_string(img))

3、打碼平臺（雲打碼）

from YDMHTTPDemo3 import YDMHttp
'''打碼平臺：雲打碼
             打碼兔'''

######################################################################

# 用戶名
username    = 'mianxiang_mei'

# 密碼
password    = 'gjp625262'

# 軟件ＩＤ，開發者分紅必要參數。登陸開發者後臺【個人軟件】得到！
appid       = 8212

# 軟件密鑰，開發者分紅必要參數。登陸開發者後臺【個人軟件】得到！
appkey      = 'dbd2645a635701a0a9f19fd0072d82c3'

# 圖片文件
filename    = 'img/code.png'

# 驗證碼類型，# 例：1004表示4位字母數字，不一樣類型收費不一樣。請準確填寫，不然影響識別率。在此查詢全部類型 http://www.yundama.com/price.html
codetype    = 1004

# 超時時間，秒
timeout     = 60

# 檢查
if (username == 'username'):
    print('請設置好相關參數再測試')
else:
    # 初始化
    yundama = YDMHttp(username, password, appid, appkey)

    # 登錄雲打碼
    uid = yundama.login();
    print('uid: %s' % uid)

    # 查詢餘額
    balance = yundama.balance();
    print('balance: %s' % balance)

    # 開始識別，圖片路徑，驗證碼類型ID，超時時間（秒），識別結果
    cid, result = yundama.decode(filename, codetype, timeout);
    print('cid: %s, result: %s' % (cid, result))

######################################################################

附：雲打碼調用的類

import http.client, mimetypes, urllib, json, time, requests

######################################################################

class YDMHttp:

    apiurl = 'http://api.yundama.com/api.php'
    username = ''
    password = ''
    appid = ''
    appkey = ''

    def __init__(self, username, password, appid, appkey):
        self.username = username  
        self.password = password
        self.appid = str(appid)
        self.appkey = appkey

    def request(self, fields, files=[]):
        response = self.post_url(self.apiurl, fields, files)
        response = json.loads(response)
        return response
    
    def balance(self):
        data = {'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['balance']
        else:
            return -9001
    
    def login(self):
        data = {'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['uid']
        else:
            return -9001

    def upload(self, filename, codetype, timeout):
        data = {'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)}
        file = {'file': filename}
        response = self.request(data, file)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['cid']
        else:
            return -9001

    def result(self, cid):
        data = {'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'cid': str(cid)}
        response = self.request(data)
        return response and response['text'] or ''

    def decode(self, filename, codetype, timeout):
        cid = self.upload(filename, codetype, timeout)
        if (cid > 0):
            for i in range(0, timeout):
                result = self.result(cid)
                if (result != ''):
                    return cid, result
                else:
                    time.sleep(1)
            return -3003, ''
        else:
            return cid, ''

    def report(self, cid):
        data = {'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'cid': str(cid), 'flag': '0'}
        response = self.request(data)
        if (response):
            return response['ret']
        else:
            return -9001

    def post_url(self, url, fields, files=[]):
        for key in files:
            files[key] = open(files[key], 'rb');
        res = requests.post(url, files=files, data=fields)
        return res.text