{"id":1115652,"date":"2025-01-08T18:08:52","date_gmt":"2025-01-08T10:08:52","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1115652.html"},"modified":"2025-01-08T18:08:54","modified_gmt":"2025-01-08T10:08:54","slug":"python%e7%88%ac%e8%99%ab%e4%b8%ad%e5%a6%82%e4%bd%95%e5%a4%84%e7%90%86%e9%aa%8c%e8%af%81%e7%a0%81-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1115652.html","title":{"rendered":"python\u722c\u866b\u4e2d\u5982\u4f55\u5904\u7406\u9a8c\u8bc1\u7801"},"content":{"rendered":"

\"python\u722c\u866b\u4e2d\u5982\u4f55\u5904\u7406\u9a8c\u8bc1\u7801\"<\/p>\n

\u5728Python\u722c\u866b\u4e2d\u5904\u7406\u9a8c\u8bc1\u7801\u7684\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528\u6253\u7801\u5e73\u53f0\u3001\u4f7f\u7528OCR\u8bc6\u522b\u3001\u4f7f\u7528\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u3001\u7ed5\u8fc7\u9a8c\u8bc1\u7801\u3002<\/strong> \u5176\u4e2d\uff0c\u4f7f\u7528OCR\u8bc6\u522b<\/strong>\u662f\u4e00\u79cd\u5e38\u89c1\u4e14\u6709\u6548\u7684\u65b9\u5f0f\u3002OCR\uff08Optical Character Recognition\uff0c\u5149\u5b66\u5b57\u7b26\u8bc6\u522b\uff09\u53ef\u4ee5\u5c06\u56fe\u50cf\u4e2d\u7684\u6587\u5b57\u8f6c\u6362\u4e3a\u673a\u5668\u53ef\u8bfb\u7684\u6587\u672c\u3002\u901a\u8fc7\u4f7f\u7528\u8bf8\u5982Tesseract\u7b49\u5f00\u6e90OCR\u5e93\uff0c\u53ef\u4ee5\u5728\u4e0d\u4f9d\u8d56\u5916\u90e8\u670d\u52a1\u7684\u60c5\u51b5\u4e0b\u8bc6\u522b\u9a8c\u8bc1\u7801\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u4f7f\u7528OCR\u8bc6\u522b\u9a8c\u8bc1\u7801\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528OCR\u8bc6\u522b\u9a8c\u8bc1\u7801<\/h3>\n<\/p>\n

1. \u5b89\u88c5\u548c\u914d\u7f6eTesseract<\/h4>\n<\/p>\n

Tesseract\u662f\u4e00\u4e2a\u5f00\u6e90\u7684OCR\u5de5\u5177\uff0c\u53ef\u4ee5\u8bc6\u522b\u591a\u79cd\u8bed\u8a00\u7684\u6587\u672c\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5Tesseract\u4ee5\u53caPython\u7684Pillow\u5e93\uff08\u7528\u4e8e\u56fe\u50cf\u5904\u7406\uff09\u3002<\/p>\n<\/p>\n

sudo apt-get install tesseract-ocr<\/p>\n
pip install pillow<\/p>\n
pip install pytesseract<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u9700\u8981\u786e\u4fddTesseract\u5728\u7cfb\u7edf\u8def\u5f84\u4e2d\u3002\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u6765\u9a8c\u8bc1\uff1a<\/p>\n<\/p>\n
tesseract --version<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528Pillow\u5904\u7406\u56fe\u50cf<\/h4>\n<\/p>\n
\u5728\u8bc6\u522b\u9a8c\u8bc1\u7801\u4e4b\u524d\uff0c\u901a\u5e38\u9700\u8981\u5bf9\u56fe\u50cf\u8fdb\u884c\u9884\u5904\u7406\u3002\u5e38\u89c1\u7684\u9884\u5904\u7406\u64cd\u4f5c\u5305\u62ec\u7070\u5ea6\u5316\u3001\u4e8c\u503c\u5316\u3001\u53bb\u566a\u7b49\u3002Pillow\u5e93\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u56fe\u50cf\u5904\u7406\u529f\u80fd\u3002<\/p>\n<\/p>\n
from PIL import Image, ImageEnhance, ImageFilter<\/p>\n
\u6253\u5f00\u9a8c\u8bc1\u7801\u56fe\u50cf<\/strong><\/h2>\n
image = Image.open('captcha.png')<\/p>\n
\u8f6c\u4e3a\u7070\u5ea6\u56fe\u50cf<\/strong><\/h2>\n
gray = image.convert('L')<\/p>\n
\u589e\u5f3a\u5bf9\u6bd4\u5ea6<\/strong><\/h2>\n
enhancer = ImageEnhance.Contrast(gray)<\/p>\n
gray = enhancer.enhance(2)<\/p>\n
\u4e8c\u503c\u5316<\/strong><\/h2>\n
bw = gray.point(lambda x: 0 if x < 128 else 255, '1')<\/p>\n
\u4fdd\u5b58\u5904\u7406\u540e\u7684\u56fe\u50cf<\/strong><\/h2>\n
bw.save('processed_captcha.png')<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u4f7f\u7528Tesseract\u8bc6\u522b\u9a8c\u8bc1\u7801<\/h4>\n<\/p>\n
import pytesseract<\/p>\n
\u8bc6\u522b\u9a8c\u8bc1\u7801<\/strong><\/h2>\n
text = pytesseract.image_to_string(bw)<\/p>\n
print(text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528OCR\u8bc6\u522b\u9a8c\u8bc1\u7801\u3002\u867d\u7136OCR\u8bc6\u522b\u9a8c\u8bc1\u7801\u7684\u65b9\u6cd5\u7b80\u5355\u4e14\u6709\u6548\uff0c\u4f46\u5728\u9762\u5bf9\u590d\u6742\u9a8c\u8bc1\u7801\u65f6\uff0c\u5176\u8bc6\u522b\u51c6\u786e\u7387\u53ef\u80fd\u8f83\u4f4e\uff0c\u56e0\u6b64\u9700\u8981\u7ed3\u5408\u5176\u4ed6\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528\u6253\u7801\u5e73\u53f0<\/h3>\n<\/p>\n
\u6253\u7801\u5e73\u53f0\u662f\u4e13\u4e1a\u5904\u7406\u9a8c\u8bc1\u7801\u7684\u670d\u52a1\uff0c\u901a\u8fc7\u5c06\u9a8c\u8bc1\u7801\u56fe\u7247\u53d1\u9001\u81f3\u6253\u7801\u5e73\u53f0\uff0c\u83b7\u5f97\u8bc6\u522b\u7ed3\u679c\u3002\u5e38\u89c1\u7684\u6253\u7801\u5e73\u53f0\u5305\u62ec\u4e91\u6253\u7801\u3001\u8d85\u7ea7\u9e70\u7b49\u3002\u4f7f\u7528\u6253\u7801\u5e73\u53f0\u65f6\uff0c\u9700\u8981\u6ce8\u518c\u8d26\u53f7\u5e76\u83b7\u53d6API Key\u3002<\/p>\n<\/p>\n
1. \u5b89\u88c5\u7b2c\u4e09\u65b9\u5e93<\/h4>\n<\/p>\n
pip install requests<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u53d1\u9001\u9a8c\u8bc1\u7801\u56fe\u7247\u81f3\u6253\u7801\u5e73\u53f0<\/h4>\n<\/p>\n
import requests<\/p>\n
api_key = 'your_api_key'<\/p>\n
url = 'https:\/\/api.dama2.com:7766\/app\/d2Url'<\/p>\n
image_path = 'captcha.png'<\/p>\n
with open(image_path, 'rb') as f:<\/p>\n
    files = {'file': f}<\/p>\n
    response = requests.post(url, files=files, data={'apiKey': api_key})<\/p>\n
    result = response.json()<\/p>\n
    print(result)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u6253\u7801\u5e73\u53f0\u80fd\u591f\u63d0\u4f9b\u9ad8\u51c6\u786e\u7387\u7684\u9a8c\u8bc1\u7801\u8bc6\u522b\u7ed3\u679c\uff0c\u4f46\u9700\u8981\u652f\u4ed8\u4e00\u5b9a\u8d39\u7528\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528\u6d4f\u89c8\u5668\u81ea\u52a8\u5316<\/h3>\n<\/p>\n
\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\uff08\u5982Selenium\uff09\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff0c\u5904\u7406\u590d\u6742\u9a8c\u8bc1\u7801\u3002\u901a\u8fc7\u6a21\u62df\u7528\u6237\u5728\u6d4f\u89c8\u5668\u4e2d\u7684\u64cd\u4f5c\uff0c\u53ef\u4ee5\u6709\u6548\u5e94\u5bf9\u52a8\u6001\u7f51\u9875\u548c\u590d\u6742\u9a8c\u8bc1\u7801\u3002<\/p>\n<\/p>\n
1. \u5b89\u88c5Selenium<\/h4>\n<\/p>\n
pip install selenium<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u7f16\u5199\u81ea\u52a8\u5316\u811a\u672c<\/h4>\n<\/p>\n
from selenium import webdriver<\/p>\n
from selenium.webdriver.common.by import By<\/p>\n
\u521d\u59cb\u5316\u6d4f\u89c8\u5668\u9a71\u52a8<\/strong><\/h2>\n
driver = webdriver.Chrome()<\/p>\n
\u6253\u5f00\u76ee\u6807\u7f51\u7ad9<\/strong><\/h2>\n
driver.get('https:\/\/www.example.com')<\/p>\n
\u67e5\u627e\u9a8c\u8bc1\u7801\u56fe\u7247\u5e76\u622a\u56fe<\/strong><\/h2>\n
captcha_element = driver.find_element(By.ID, 'captcha_image')<\/p>\n
captcha_element.screenshot('captcha.png')<\/p>\n
\u624b\u52a8\u8f93\u5165\u9a8c\u8bc1\u7801\u6216\u4f7f\u7528\u6253\u7801\u5e73\u53f0\u8bc6\u522b<\/strong><\/h2>\n
captcha_code = input('\u8bf7\u8f93\u5165\u9a8c\u8bc1\u7801\uff1a')<\/p>\n
\u586b\u5199\u9a8c\u8bc1\u7801\u5e76\u63d0\u4ea4\u8868\u5355<\/strong><\/h2>\n
captcha_input = driver.find_element(By.ID, 'captcha_input')<\/p>\n
captcha_input.send_keys(captcha_code)<\/p>\n
submit_button = driver.find_element(By.ID, 'submit_button')<\/p>\n
submit_button.click()<\/p>\n
\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n
driver.quit()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u53ef\u4ee5\u5904\u7406\u590d\u6742\u4ea4\u4e92\uff0c\u4f46\u9700\u8981\u5b89\u88c5\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u5e76\u4e14\u8fd0\u884c\u6548\u7387\u8f83\u4f4e\u3002<\/p>\n<\/p>\n
\u56db\u3001\u7ed5\u8fc7\u9a8c\u8bc1\u7801<\/h3>\n<\/p>\n
\u7ed5\u8fc7\u9a8c\u8bc1\u7801\u662f\u6307\u901a\u8fc7\u5176\u4ed6\u65b9\u6cd5\u907f\u514d\u89e6\u53d1\u9a8c\u8bc1\u7801\u3002\u4f8b\u5982\uff0c\u901a\u8fc7\u89e3\u6790\u7f51\u7ad9\u7684API\u63a5\u53e3\u83b7\u53d6\u6570\u636e\uff0c\u6216\u901a\u8fc7\u4f2a\u9020\u8bf7\u6c42\u907f\u514d\u9a8c\u8bc1\u7801\u9a8c\u8bc1\u3002<\/p>\n<\/p>\n
1. \u89e3\u6790API\u63a5\u53e3<\/h4>\n<\/p>\n
\u8bb8\u591a\u7f51\u7ad9\u7684\u524d\u7aef\u9875\u9762\u4e0e\u540e\u7aefAPI\u63a5\u53e3\u662f\u5206\u79bb\u7684\uff0c\u901a\u8fc7\u5206\u6790\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u53ef\u4ee5\u627e\u5230\u76f4\u63a5\u83b7\u53d6\u6570\u636e\u7684API\u63a5\u53e3\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'https:\/\/api.example.com\/data'<\/p>\n
response = requests.get(url)<\/p>\n
data = response.json()<\/p>\n
print(data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f2a\u9020\u8bf7\u6c42<\/h4>\n<\/p>\n
\u901a\u8fc7\u4f2a\u9020\u8bf7\u6c42\u5934\uff0c\u53ef\u4ee5\u6a21\u62df\u6b63\u5e38\u7528\u6237\u8bf7\u6c42\uff0c\u907f\u514d\u89e6\u53d1\u9a8c\u8bc1\u7801\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'https:\/\/www.example.com\/login'<\/p>\n
headers = {<\/p>\n
    'User-Agent': 'Mozilla\/5.0',<\/p>\n
    'Referer': 'https:\/\/www.example.com'<\/p>\n
}<\/p>\n
data = {<\/p>\n
    'username': 'your_username',<\/p>\n
    'password': 'your_password'<\/p>\n
}<\/p>\n
response = requests.post(url, headers=headers, data=data)<\/p>\n
print(response.text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f2a\u9020\u8bf7\u6c42\u9700\u8981\u5206\u6790\u8bf7\u6c42\u5934\u548c\u8bf7\u6c42\u53c2\u6570\uff0c\u6709\u4e00\u5b9a\u6280\u672f\u96be\u5ea6\u3002<\/p>\n<\/p>\n
\u603b\u7ed3<\/h3>\n<\/p>\n
\u5728Python\u722c\u866b\u4e2d\u5904\u7406\u9a8c\u8bc1\u7801\u7684\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528\u6253\u7801\u5e73\u53f0\u3001\u4f7f\u7528OCR\u8bc6\u522b\u3001\u4f7f\u7528\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u3001\u7ed5\u8fc7\u9a8c\u8bc1\u7801<\/strong>\u3002\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u4f18\u7f3a\u70b9\uff0c\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u53d6\u51b3\u4e8e\u5177\u4f53\u573a\u666f\u548c\u9700\u6c42\u3002\u901a\u8fc7\u7ed3\u5408\u591a\u79cd\u65b9\u6cd5\uff0c\u53ef\u4ee5\u63d0\u9ad8\u9a8c\u8bc1\u7801\u8bc6\u522b\u7684\u51c6\u786e\u7387\u548c\u6548\u7387\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u8bc6\u522b\u548c\u5904\u7406\u9a8c\u8bc1\u7801\u4e2d\u7684\u6587\u5b57\uff1f<\/strong>
\u5728Python\u722c\u866b\u4e2d\uff0c\u5904\u7406\u9a8c\u8bc1\u7801\u901a\u5e38\u9700\u8981\u4f7f\u7528OCR\uff08\u5149\u5b66\u5b57\u7b26\u8bc6\u522b\uff09\u6280\u672f\u3002\u53ef\u4ee5\u4f7f\u7528\u50cfTesseract\u8fd9\u6837\u7684\u5e93\u6765\u8bc6\u522b\u9a8c\u8bc1\u7801\u4e2d\u7684\u5b57\u7b26\u3002\u901a\u8fc7\u5c06\u9a8c\u8bc1\u7801\u56fe\u50cf\u8f6c\u5316\u4e3a\u7070\u5ea6\u56fe\u5e76\u8fdb\u884c\u4e8c\u503c\u5316\u5904\u7406\uff0c\u80fd\u63d0\u9ad8\u8bc6\u522b\u7684\u51c6\u786e\u6027\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u56fe\u50cf\u5904\u7406\u6280\u672f\u5982\u964d\u566a\u548c\u8fb9\u7f18\u68c0\u6d4b\u4e5f\u80fd\u5e2e\u52a9\u63d0\u9ad8OCR\u6548\u679c\u3002<\/p>\n
\u6709\u6ca1\u6709\u63a8\u8350\u7684\u5e93\u6216\u5de5\u5177\u6765\u5904\u7406\u9a8c\u8bc1\u7801\uff1f<\/strong>
\u5728\u5904\u7406\u9a8c\u8bc1\u7801\u65f6\uff0c\u5e38\u7528\u7684\u5e93\u5305\u62ecPillow\uff08\u7528\u4e8e\u56fe\u50cf\u5904\u7406\uff09\u3001Tesseract\uff08\u7528\u4e8eOCR\u8bc6\u522b\uff09\u548cRequests\uff08\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff09\u3002\u6b64\u5916\uff0c\u8fd8\u6709\u4e13\u95e8\u9488\u5bf9\u9a8c\u8bc1\u7801\u7684\u5904\u7406\u5de5\u5177\uff0c\u5982\u9a8c\u8bc1\u7801\u8bc6\u522bAPI\u6216\u7b2c\u4e09\u65b9\u670d\u52a1\uff0c\u53ef\u4ee5\u76f4\u63a5\u63d0\u4f9b\u8bc6\u522b\u7ed3\u679c\uff0c\u8282\u7701\u5f00\u53d1\u65f6\u95f4\u3002<\/p>\n
\u5982\u4f55\u7ed5\u8fc7\u590d\u6742\u7684\u9a8c\u8bc1\u7801\u673a\u5236\uff1f<\/strong>
\u5bf9\u4e8e\u590d\u6742\u7684\u9a8c\u8bc1\u7801\uff0c\u901a\u5e38\u9700\u8981\u66f4\u5148\u8fdb\u7684\u6280\u672f\uff0c\u5982\u6df1\u5ea6\u5b66\u4e60\u3002\u53ef\u4ee5\u8bad\u7ec3\u4e00\u4e2a\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\u6765\u8bc6\u522b\u7279\u5b9a\u7c7b\u578b\u7684\u9a8c\u8bc1\u7801\u3002\u6b64\u5916\uff0c\u6a21\u62df\u7528\u6237\u884c\u4e3a\u6216\u4f7f\u7528\u81ea\u52a8\u5316\u6d4b\u8bd5\u5de5\u5177\uff08\u5982Selenium\uff09\u4e5f\u53ef\u4ee5\u5e2e\u52a9\u5904\u7406\u4e00\u4e9b\u52a8\u6001\u751f\u6210\u7684\u9a8c\u8bc1\u7801\uff0c\u786e\u4fdd\u722c\u866b\u5728\u8bf7\u6c42\u65f6\u80fd\u591f\u6b63\u5e38\u901a\u8fc7\u9a8c\u8bc1\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u722c\u866b\u4e2d\u5904\u7406\u9a8c\u8bc1\u7801\u7684\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528\u6253\u7801\u5e73\u53f0\u3001\u4f7f\u7528OCR\u8bc6\u522b\u3001\u4f7f\u7528\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u3001\u7ed5\u8fc7\u9a8c\u8bc1\u7801\u3002 \u5176\u4e2d […]","protected":false},"author":3,"featured_media":1115659,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1115652"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1115652"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1115652\/revisions"}],"predecessor-version":[{"id":1115661,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1115652\/revisions\/1115661"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1115659"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1115652"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1115652"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1115652"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}