• 技术文章 >Python技术 >Python基础教程

    python如何处理掉12306的验证码

    爱喝马黛茶的安东尼爱喝马黛茶的安东尼2019-10-17 16:41:19原创2483

    本文实例讲述了Python实现破解12306图片验证码的方法。分享给大家供大家参考,具体如下:

    不知从何时起,12306的登录验证码竟然变成了按字找图,可以说是又提高了一个等次,竟然把图像识别都用上了。不过有些图片,不得不说有些变态,图片的清晰图就更别说了,明显是从网络上的图库中搬过来的。

    3de194101076ab39883b10338f1993c.png

    相关推荐:《Python基础教程

    谁知没多久,网络就惊现破解12306图片验证码的Python代码了,作为一个爱玩爱刺激的网虫,当然要分享一份过来。

    代码大致流程:

    1、将验证码图片下载下来,然后切图;

    2、利用百度识图进行图片分析;

    3、再利用正则表达式来取出百度识图的关键字,最后输出。

    代码:

    1

    2

    3

    4

    5

    6

    7

    8

    9

    10

    11

    12

    13

    14

    15

    16

    17

    18

    19

    20

    21

    22

    23

    24

    25

    26

    27

    28

    29

    30

    31

    32

    33

    34

    35

    36

    37

    38

    39

    40

    41

    42

    43

    44

    45

    46

    47

    48

    49

    50

    51

    52

    53

    54

    55

    56

    57

    58

    59

    60

    61

    62

    63

    64

    65

    66

    67

    68

    69

    70

    71

    72

    73

    74

    75

    76

    77

    78

    79

    80

    81

    82

    83

    84

    85

    86

    87

    88

    89

    90

    91

    92

    93

    94

    95

    96

    97

    98

    99

    100

    101

    102

    103

    104

    105

    106

    107

    108

    #!/usr/bin/python

    # # FileName  : fuck12306.py

    # # Author   : MaoMao Wang <andelf@gmail.com>

    # # Created   : Mon Mar 16 22:08:41 2015 by ShuYu Wang

    # # Copyright  : Feather (c) 2015

    # # Description : fuck fuck 12306

    # # Time-stamp: <2015-03-17 10:57:44 andelf>

    from PIL import Image

    from PIL import ImageFilter

    import urllib

    import urllib2

    import re

    import json

    # hack CERTIFICATE_VERIFY_FAILED

    # https://github.com/mtschirs/quizduellapi/issues/2

    import ssl

    if hasattr(ssl, '_create_unverified_context'):

        ssl._create_default_https_context = ssl._create_unverified_context

    UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome

    /41.0.2272.89 Safari/537.36"

    pic_url = "https://kyfw.12306.cn/otn/passcodeNew/getPassCodeNew?module=login&rand=sjrand&0.21191171556711197"

    def get_img():

        resp = urllib.urlopen(pic_url)

        raw = resp.read()

        with open("./tmp.jpg", 'wb') as fp:

            fp.write(raw)

        return Image.open("./tmp.jpg")

    def get_sub_img(im, x, y):

        assert 0 <= x <= 3

        assert 0 <= y <= 2

        WITH = HEIGHT = 68

        left = 5 + (67 + 5) * x

        top = 41 + (67 + 5) * y

        right = left + 67

        bottom = top + 67

        return im.crop((left, top, right, bottom))

    def baidu_stu_lookup(im):

        url = "http://stu.baidu.com/n/image?fr=html5&needRawImageUrl=true&id=WU_FILE_0&name=233.png&type=

        image%2Fpng&lastModifiedDate=Mon+Mar+16+2015+20%3A49%3A11+GMT%2B0800+(CST)&size="

        im.save("./query_temp_img.png")

        raw = open("./query_temp_img.png", 'rb').read()

        url = url + str(len(raw))

        req = urllib2.Request(url, raw, {'Content-Type':'image/png', 'User-Agent':UA})

        resp = urllib2.urlopen(req)

        resp_url = resp.read()   # return a pure url

        url = "http://stu.baidu.com/n/searchpc?queryImageUrl=" + urllib.quote(resp_url)

        req = urllib2.Request(url, headers={'User-Agent':UA})

        resp = urllib2.urlopen(req)

        html = resp.read()

        return baidu_stu_html_extract(html)

    def baidu_stu_html_extract(html):

        #pattern = re.compile(r'<script type="text/javascript">(.*?)</script>', re.DOTALL | re.MULTILINE)

        pattern = re.compile(r"keywords:'(.*?)'")

        matches = pattern.findall(html)

        if not matches:

            return '[UNKNOWN]'

        json_str = matches[0]

        json_str = json_str.replace('\\x22', '"').replace('\\\\', '\\')

        #print json_str

        result = [item['keyword'] for item in json.loads(json_str)]

        return '|'.join(result) if result else '[UNKNOWN]'

    def ocr_question_extract(im):

        # git@github.com:madmaze/pytesseract.git

        global pytesseract

        try:

            import pytesseract

        except:

            print "[ERROR] pytesseract not installed"

            return

        im = im.crop((127, 3, 260, 22))

        im = pre_ocr_processing(im)

        # im.show()

        return pytesseract.image_to_string(im,).strip()

    def pre_ocr_processing(im):

        im = im.convert("RGB")

        width, height = im.size

        white = im.filter(ImageFilter.BLUR).filter(ImageFilter.MaxFilter(23))

        grey = im.convert('L')

        impix = im.load()

        whitepix = white.load()

        greypix = grey.load()

        for y in range(height):

            for x in range(width):

                greypix[x,y] = min(255, max(255 + impix[x,y][0] - whitepix[x,y][0],

                    255 + impix[x,y][1] - whitepix[x,y][1],

                    255 + impix[x,y][2] - whitepix[x,y][2]))

        new_im = grey.copy()

        binarize(new_im, 150)

        return new_im

    def binarize(im, thresh=120):

        assert 0 < thresh < 255

        assert im.mode == 'L'

        w, h = im.size

        for y in xrange(0, h):

            for x in xrange(0, w):

                if im.getpixel((x,y)) < thresh:

                    im.putpixel((x,y), 0)

                else:

                    im.putpixel((x,y), 255)

    if __name__ == '__main__':

        im = get_img()

        #im = Image.open("./tmp.jpg")

        print 'OCR Question:', ocr_question_extract(im)

        for y in range(2):

            for x in range(4):

                im2 = get_sub_img(im, x, y)

                result = baidu_stu_lookup(im2)

                print (y,x), result

    专题推荐:python 处理 12306 验证码
    上一篇:Python无法验证ssl证书怎么解决 下一篇:python是汇编语言吗

    相关文章推荐

    • Python脚本绘制验证码

    全部评论我要评论

    © 2021 Python学习网 苏ICP备2021003149号-1

  • 取消发布评论
  • 

    Python学习网