Python爬虫基础：验证码的爬取和识别详解

import requests
import os
import time
from lxml import etree


def get_Page(url,headers):
    response = requests.get(url,headers=headers)
    if response.status_code == 200:
        # print(response.text)
        return response.text
    return None


def parse_Page(html,headers):
    html_lxml = etree.HTML(html)
    datas = html_lxml.xpath('.//div[@class="captcha_images_left"]|.//div[@class="captcha_images_right"]')
    item= {}
    # 创建保存验证码文件夹
    file = 'D:/******'
    if os.path.exists(file):
        os.chdir(file)
    else:    
        os.mkdir(file)
        os.chdir(file)    
    for data in datas:
        # 验证码名称
        name = data.xpath('.//h3')
        # print(len(name))
        # 验证码链接
        src = data.xpath('.//div/img/@src')    
        # print(len(src))
        count = 0
        for i in range(len(name)):
            # 验证码图片文件名
            filename = name[i].text + '.jpg'
            img_url = 'https://captcha.com/' + src[i]
            response = requests.get(img_url,headers=headers)
            if response.status_code == 200:
                image = response.content
                with open(filename,'wb') as f:
                    f.write(image)
                    count += 1
                    print('保存第{}张验证码成功'.format(count))
                    time.sleep(1)


def main():
    url = 'https://captcha.com/captcha-examples.html?cst=corg'
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'}
    html = get_Page(url,headers)
    parse_Page(html,headers)


if __name__ == '__main__':
    main()

datas = html_lxml.xpath('.//div[@class="captcha_images_left"]|.//div[@class="captcha_images_right"]')

from aip import AipOcr

#  你的 APPID AK SK 
APP_ID = '你的 APP_ID '
API_KEY = '你的API_KEY'
SECRET_KEY = '你的SECRET_KEY'

client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

# 读取图片 
def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
        return fp.read()

image = get_file_content('test.jpg')

#  调用通用文字识别, 图片参数为本地图片 
result = client.basicGeneral(image)


# 定义参数变量  
options = {
    # 定义图像方向
        'detect_direction' : 'true',
    # 识别语言类型，默认为'CHN_ENG'中英文混合
        'language_type' : 'CHN_ENG',


}

# 调用通用文字识别接口  
result = client.basicGeneral(image,options)
print(result)
for word in result['words_result']:
    print(word['words'])

from aip import AipOcr
import os


i = 0
j = 0
APP_ID = '你的 APP_ID '
API_KEY = '你的API_KEY'
SECRET_KEY = '你的SECRET_KEY'

client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

# 读取图片 
file_path = 'D:\******\验证码图片'
filenames = os.listdir(file_path)
# print(filenames)
for filename in filenames:
    # 将路径与文件名结合起来就是每个文件的完整路径
    info = os.path.join(file_path,filename)
    with open(info, 'rb') as fp:
        # 获取文件夹的路径    
        image = fp.read()
        # 调用通用文字识别, 图片参数为本地图片
        result = client.basicGeneral(image)
        # 定义参数变量  
        options = {
                'detect_direction' : 'true',
                'language_type' : 'CHN_ENG',
        }
        # 调用通用文字识别接口  
        result = client.basicGeneral(image,options)
        # print(result)
        if result['words_result_num'] == 0:
            print(filename + ':' + '----')
            i += 1
        else:
            for word in result['words_result']:                    
                print(filename + ' : ' +word['words'])
                j += 1

print('共识别验证码{}张'.format(i+j))
print('未识别出文本{}张'.format(i))
print('已识别出文本{}张'.format(j))

from PIL import Image

filepath = 'D:\******\验证码图片\AncientMosaic Captcha Image.jpg'
image = Image.open(filepath)
# 传入'L'将图片转化为灰度图像
image = image.convert('L')
# 传入'1'将图片进行二值化处理
image = image.convert('1')
image.show()

from PIL import Image

filepath = 'D:\******\验证码图片\AncientMosaic Captcha Image.bmp'
image = Image.open(filepath)
# 传入'L'将图片转化为灰度图像
image = image.convert('L')
# 传入'l'将图片进行二值化处理,默认二值化阈值为127
# 指定阈值进行转化
count= 170
table = []
for i in range(256):
    if i < count:
        table.append(0)
    else:
        table.append(1 )
image = image.point(table,'1')
image.show()

# 找到边缘
image = image.filter(ImageFilter.FIND_EDGES)
# image.show()
# 边缘增强
image = image.filter(ImageFilter.EDGE_ENHANCE)
image.show()

from PIL import Image,ImageFilter

filepath = 'D:\******\验证码图片\CrossShadow2 Captcha Image.jpg'
image = Image.open(filepath)
# 传入'L'将图片转化为灰度图像
image = image.convert('L')

# 传入'l'将图片进行二值化处理,默认二值化阈值为127
# 指定阈值进行转化
count= 230
table = []
for i in range(256):
    if i < count:
        table.append(1)
    else:
        table.append(0)
image = image.point(table,'1')
image.show()