GitLab

# 测试代码
def get_daoyou_chaxun_code(
        user_agent='Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36',
        cookie='ASPSESSIONIDAACBQDRC=CLLNDELDHNFCMPNHJGFPMDOP; ASPSESSIONIDACACRCRD=EOJHODNDAKFGHKEHEBECAKFB'
):
    # 打开图片
    import io
    import requests

    r = requests.get('http://daoyou-chaxun.cnta.gov.cn/single_info/validatecode.asp', headers={
        "User-Agent": user_agent,
        "Cookie":cookie
    }, timeout=20)
    imageData = r.content
    data_stream = io.BytesIO(imageData)
    image = Image.open(data_stream)
    enhancer = ImageEnhance.Contrast(image)
    enhancer.enhance(3)

    # 将图片转换成灰度图片
    image = image.convert("L")

    # 二值化
    twoValue(image)

    # 分割图片
    next_line = True
    last_empty_line = True
    start_xs = []
    end_xs = []
    for x in range(image.size[0]):
        empty_line = True
        for y in range(image.size[1]):
            L = image.getpixel((x, y))
            if L < 200:
                empty_line = False
                next_line = True
        if not empty_line:
            if last_empty_line:
                start_xs.append(x)
        if empty_line and next_line:
            end_xs.append(x - 1)
            next_line = False
        if empty_line:
            last_empty_line = True
        else:
            last_empty_line = False

    # 数字特征库
    signature_list = [
        # 0
        [(0, 0, 0), (0, 9, 0), (5, 0, 0), (5, 9, 0), (0, 1, 1), (0, 2, 1), (0, 3, 1), (0, 4, 1), (0, 5, 1), (0, 6, 1),
         (0, 7, 1), (0, 8, 1)],
        # 1
        [(0, 0, 0), (0, 1, 1), (0, 9, 1), (0, 5, 0)],
        # 2
        [(0, 7, 0), (1, 7, 1), (1, 6, 0), (2, 6, 1)],
        # 3
        [(0, 4, 0), (1, 4, 0), (2, 4, 1)],
        # 4
        [(0, 9, 0), (1, 9, 0), (2, 9, 0), (3, 9, 1), (4, 9, 1), (5, 9, 1)],
        # 5
        [(0, 4, 1), (0, 5, 0), (0, 6, 0), (0, 7, 0), (0, 8, 1), (0, 9, 0)],
        # 6
        [(0, 0, 0), (0, 1, 0), (1, 0, 0), (2, 0, 1)],
        # 7
        [(0, 0, 1), (0, 1, 1), (0, 2, 0), (0, 3, 0), (0, 4, 0), (0, 5, 0), (0, 6, 0), (1, 8, 1), (1, 9, 1), (1, 7, 0)],
        # 8
        [(0, 0, 0), (0, 9, 0), (5, 0, 0), (0, 4, 0), (1, 0, 1), (0, 1, 1)],
        # 9
        [(0, 4, 1), (0, 5, 0), (0, 6, 0), (0, 7, 0), (0, 8, 0), (0, 9, 0), (1, 9, 1), (2, 9, 1), (3, 9, 1)],
    ]

    result = []
    for i in range(len(start_xs)):
        s_offset = start_xs[i]
        e_offset = end_xs[i]
        if (e_offset - s_offset) == 4:
            result.append('1')
            continue
        num = 0
        for signature in signature_list:
            # print signature
            if num == 1:  # 数字1不判断,因为前边已经判断过了
                num += 1
                continue
            # print '特征:',num
            match = True
            for pp in signature:
                x = pp[0]
                y = pp[1]
                is_p = pp[2]
                if checkIsPoint(image, (s_offset + x, y)) is not is_p:
                    match = False
                    break
            if match:
                result.append(str(num))
                break

            num += 1
    return result