{"id":1067101,"date":"2024-12-31T16:31:59","date_gmt":"2024-12-31T08:31:59","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1067101.html"},"modified":"2024-12-31T16:32:03","modified_gmt":"2024-12-31T08:32:03","slug":"python3%e5%a6%82%e4%bd%95%e8%8e%b7%e5%8f%96%e9%aa%8c%e8%af%81%e7%a0%81","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1067101.html","title":{"rendered":"python3\u5982\u4f55\u83b7\u53d6\u9a8c\u8bc1\u7801"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/6265e887-5ccc-4ff3-9813-33ea1ec70006.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"python3\u5982\u4f55\u83b7\u53d6\u9a8c\u8bc1\u7801\" \/><\/p>\n<p><p> <strong>Python3\u83b7\u53d6\u9a8c\u8bc1\u7801\u7684\u65b9\u6cd5\u5305\u62ecrequests\u5e93\u3001BeautifulSoup\u5e93\u3001pytesseract\u5e93\u3001\u4ee5\u53ca\u5176\u4ed6\u5982selenium\u5e93\u7b49\u3002\u4f7f\u7528requests\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001HTTP\u8bf7\u6c42\u3001BeautifulSoup\u5e93\u7528\u4e8e\u89e3\u6790HTML\u5185\u5bb9\u3001pytesseract\u5e93\u7528\u4e8e\u9a8c\u8bc1\u7801\u56fe\u7247\u7684\u6587\u5b57\u8bc6\u522b\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528\u8fd9\u4e9b\u5e93\u6765\u83b7\u53d6\u5e76\u89e3\u6790\u9a8c\u8bc1\u7801\u3002<\/strong><\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/h3>\n<\/p>\n<p><p>requests\u5e93\u662fPython\u4e2d\u6700\u5e38\u7528\u7684HTTP\u8bf7\u6c42\u5e93\u4e4b\u4e00\u3002\u901a\u8fc7requests\u5e93\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u53d1\u9001\u5404\u79cdHTTP\u8bf7\u6c42\u6765\u83b7\u53d6\u9a8c\u8bc1\u7801\u56fe\u7247\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5requests\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5requests\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u9a8c\u8bc1\u7801\u56fe\u7247<\/h4>\n<\/p>\n<p><p>\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u6765\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u9a8c\u8bc1\u7801\u56fe\u7247\u7684\u4e8c\u8fdb\u5236\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com\/captcha.jpg&#39;  # \u66ff\u6362\u4e3a\u9a8c\u8bc1\u7801\u56fe\u7247\u7684\u5b9e\u9645URL<\/p>\n<p>response = requests.get(url)<\/p>\n<p>if response.status_code == 200:<\/p>\n<p>    with open(&#39;captcha.jpg&#39;, &#39;wb&#39;) as f:<\/p>\n<p>        f.write(response.content)<\/p>\n<p>    print(&#39;\u9a8c\u8bc1\u7801\u56fe\u7247\u5df2\u4fdd\u5b58&#39;)<\/p>\n<p>else:<\/p>\n<p>    print(&#39;\u83b7\u53d6\u9a8c\u8bc1\u7801\u56fe\u7247\u5931\u8d25&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML<\/h3>\n<\/p>\n<p><p>BeautifulSoup\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u7684Python\u5e93\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u6765\u89e3\u6790\u5305\u542b\u9a8c\u8bc1\u7801\u56fe\u7247\u7684\u7f51\u9875\uff0c\u5e76\u63d0\u53d6\u9a8c\u8bc1\u7801\u56fe\u7247\u7684URL\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5BeautifulSoup\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5BeautifulSoup\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install beautifulsoup4<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u89e3\u6790\u5305\u542b\u9a8c\u8bc1\u7801\u56fe\u7247\u7684\u7f51\u9875<\/h4>\n<\/p>\n<p><p>\u5047\u8bbe\u9a8c\u8bc1\u7801\u56fe\u7247\u7684URL\u4f4d\u4e8e\u7f51\u9875\u7684\u67d0\u4e2aimg\u6807\u7b7e\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u6765\u89e3\u6790\u7f51\u9875\u5e76\u63d0\u53d6\u56fe\u7247\u7684URL\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>html = &quot;&quot;&quot;<\/p>\n<p>&lt;html&gt;<\/p>\n<p>&lt;head&gt;&lt;title&gt;Example&lt;\/title&gt;&lt;\/head&gt;<\/p>\n<p>&lt;body&gt;<\/p>\n<p>&lt;img src=&quot;http:\/\/example.com\/captcha.jpg&quot; alt=&quot;captcha&quot;&gt;<\/p>\n<p>&lt;\/body&gt;<\/p>\n<p>&lt;\/html&gt;<\/p>\n<p>&quot;&quot;&quot;<\/p>\n<p>soup = BeautifulSoup(html, &#39;html.parser&#39;)<\/p>\n<p>img_tag = soup.find(&#39;img&#39;, {&#39;alt&#39;: &#39;captcha&#39;})<\/p>\n<p>if img_tag:<\/p>\n<p>    captcha_url = img_tag[&#39;src&#39;]<\/p>\n<p>    print(&#39;\u9a8c\u8bc1\u7801\u56fe\u7247URL:&#39;, captcha_url)<\/p>\n<p>else:<\/p>\n<p>    print(&#39;\u672a\u627e\u5230\u9a8c\u8bc1\u7801\u56fe\u7247&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528pytesseract\u5e93\u8fdb\u884c\u9a8c\u8bc1\u7801\u8bc6\u522b<\/h3>\n<\/p>\n<p><p>pytesseract\u662f\u4e00\u4e2a\u7528\u4e8eOCR\uff08\u5149\u5b66\u5b57\u7b26\u8bc6\u522b\uff09\u7684Python\u5e93\uff0c\u53ef\u4ee5\u5c06\u56fe\u7247\u4e2d\u7684\u6587\u5b57\u8f6c\u6362\u4e3a\u6587\u672c\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528pytesseract\u5e93\u6765\u8bc6\u522b\u9a8c\u8bc1\u7801\u56fe\u7247\u4e2d\u7684\u6587\u5b57\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5pytesseract\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5pytesseract\u5e93\u548cTesseract-OCR\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install pytesseract<\/p>\n<p>sudo apt-get install tesseract-ocr  # \u5bf9\u4e8eLinux\u7528\u6237<\/p>\n<p>brew install tesseract  # \u5bf9\u4e8emacOS\u7528\u6237<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u8bc6\u522b\u9a8c\u8bc1\u7801\u56fe\u7247\u4e2d\u7684\u6587\u5b57<\/h4>\n<\/p>\n<p><p>\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528pytesseract\u5e93\u6765\u8bc6\u522b\u9a8c\u8bc1\u7801\u56fe\u7247\u4e2d\u7684\u6587\u5b57\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from PIL import Image<\/p>\n<p>import pytesseract<\/p>\n<p>image = Image.open(&#39;captcha.jpg&#39;)<\/p>\n<p>captcha_text = pytesseract.image_to_string(image)<\/p>\n<p>print(&#39;\u9a8c\u8bc1\u7801\u6587\u5b57:&#39;, captcha_text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u4f7f\u7528selenium\u5e93\u8fdb\u884c\u7f51\u9875\u81ea\u52a8\u5316<\/h3>\n<\/p>\n<p><p>selenium\u662f\u4e00\u4e2a\u7528\u4e8e\u7f51\u9875\u81ea\u52a8\u5316\u6d4b\u8bd5\u7684Python\u5e93\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528selenium\u5e93\u6765\u6a21\u62df\u7528\u6237\u884c\u4e3a\uff0c\u81ea\u52a8\u586b\u5199\u5e76\u63d0\u4ea4\u5305\u542b\u9a8c\u8bc1\u7801\u7684\u8868\u5355\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5selenium\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5selenium\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u4f7f\u7528selenium\u8fdb\u884c\u7f51\u9875\u81ea\u52a8\u5316<\/h4>\n<\/p>\n<p><p>\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528selenium\u5e93\u6765\u81ea\u52a8\u5316\u83b7\u53d6\u9a8c\u8bc1\u7801\u56fe\u7247\u5e76\u8f93\u5165\u8bc6\u522b\u7ed3\u679c\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>from PIL import Image<\/p>\n<p>import pytesseract<\/p>\n<p>import time<\/p>\n<h2><strong>\u66ff\u6362\u4e3a\u6d4f\u89c8\u5668\u9a71\u52a8\u7684\u5b9e\u9645\u8def\u5f84<\/strong><\/h2>\n<p>driver = webdriver.Chrome(executable_path=&#39;\/path\/to\/chromedriver&#39;)<\/p>\n<p>driver.get(&#39;http:\/\/example.com\/captcha_page&#39;)  # \u66ff\u6362\u4e3a\u5b9e\u9645\u7684URL<\/p>\n<h2><strong>\u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/strong><\/h2>\n<p>time.sleep(2)<\/p>\n<h2><strong>\u83b7\u53d6\u9a8c\u8bc1\u7801\u56fe\u7247\u5143\u7d20<\/strong><\/h2>\n<p>captcha_element = driver.find_element_by_id(&#39;captcha_image&#39;)  # \u66ff\u6362\u4e3a\u5b9e\u9645\u7684\u5143\u7d20ID<\/p>\n<p>captcha_element.screenshot(&#39;captcha.png&#39;)<\/p>\n<h2><strong>\u8bc6\u522b\u9a8c\u8bc1\u7801\u6587\u5b57<\/strong><\/h2>\n<p>image = Image.open(&#39;captcha.png&#39;)<\/p>\n<p>captcha_text = pytesseract.image_to_string(image)<\/p>\n<p>print(&#39;\u9a8c\u8bc1\u7801\u6587\u5b57:&#39;, captcha_text)<\/p>\n<h2><strong>\u8f93\u5165\u9a8c\u8bc1\u7801\u5e76\u63d0\u4ea4\u8868\u5355<\/strong><\/h2>\n<p>captcha_input = driver.find_element_by_id(&#39;captcha_input&#39;)  # \u66ff\u6362\u4e3a\u5b9e\u9645\u7684\u5143\u7d20ID<\/p>\n<p>captcha_input.send_keys(captcha_text)<\/p>\n<p>submit_button = driver.find_element_by_id(&#39;submit_button&#39;)  # \u66ff\u6362\u4e3a\u5b9e\u9645\u7684\u5143\u7d20ID<\/p>\n<p>submit_button.click()<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6211\u4eec\u4ecb\u7ecd\u4e86\u5982\u4f55\u4f7f\u7528requests\u5e93\u3001BeautifulSoup\u5e93\u3001pytesseract\u5e93\u548cselenium\u5e93\u6765\u83b7\u53d6\u5e76\u89e3\u6790\u9a8c\u8bc1\u7801\u3002<strong>requests\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001HTTP\u8bf7\u6c42\u3001BeautifulSoup\u5e93\u7528\u4e8e\u89e3\u6790HTML\u5185\u5bb9\u3001pytesseract\u5e93\u7528\u4e8e\u9a8c\u8bc1\u7801\u56fe\u7247\u7684\u6587\u5b57\u8bc6\u522b\u3001selenium\u5e93\u7528\u4e8e\u7f51\u9875\u81ea\u52a8\u5316\u3002<\/strong>\u8fd9\u4e9b\u5e93\u7684\u7ec4\u5408\u4f7f\u7528\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u5728Python\u4e2d\u5b9e\u73b0\u9a8c\u8bc1\u7801\u7684\u83b7\u53d6\u548c\u89e3\u6790\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u5b9e\u9645\u573a\u666f\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python3\u83b7\u53d6\u9a8c\u8bc1\u7801\u7684\u57fa\u672c\u6b65\u9aa4\u662f\u4ec0\u4e48\uff1f<\/strong><br \/>\u83b7\u53d6\u9a8c\u8bc1\u7801\u7684\u57fa\u672c\u6b65\u9aa4\u5305\u62ec\uff1a\u9996\u5148\uff0c\u786e\u5b9a\u9a8c\u8bc1\u7801\u7684\u6765\u6e90\uff0c\u4f8b\u5982\u7f51\u9875\u3001API\u6216\u56fe\u50cf\u6587\u4ef6\u3002\u63a5\u4e0b\u6765\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u5e93\uff0c\u5982<code>requests<\/code>\u83b7\u53d6\u9a8c\u8bc1\u7801\u7684\u56fe\u50cf\u6216\u6570\u636e\u3002\u5982\u679c\u9a8c\u8bc1\u7801\u662f\u56fe\u50cf\u683c\u5f0f\uff0c\u8fd8\u9700\u8981\u4f7f\u7528\u56fe\u50cf\u5904\u7406\u5e93\u5982<code>Pillow<\/code>\u8fdb\u884c\u9884\u5904\u7406\u3002\u6700\u540e\uff0c\u901a\u8fc7OCR\u5e93\u5982<code>pytesseract<\/code>\u63d0\u53d6\u6587\u672c\u9a8c\u8bc1\u7801\u3002<\/p>\n<p><strong>Python3\u4e2d\u6709\u54ea\u4e9b\u5e93\u53ef\u4ee5\u5e2e\u52a9\u83b7\u53d6\u548c\u8bc6\u522b\u9a8c\u8bc1\u7801\uff1f<\/strong><br \/>\u5728Python3\u4e2d\uff0c\u5e38\u7528\u7684\u5e93\u6709<code>requests<\/code>\u7528\u4e8eHTTP\u8bf7\u6c42\uff0c<code>BeautifulSoup<\/code>\u7528\u4e8e\u89e3\u6790HTML\u5185\u5bb9\uff0c\u4ee5\u53ca<code>Pillow<\/code>\u7528\u4e8e\u56fe\u50cf\u5904\u7406\u3002\u6b64\u5916\uff0c<code>pytesseract<\/code>\u662f\u4e00\u4e2a\u5f3a\u5927\u7684OCR\u5de5\u5177\uff0c\u53ef\u4ee5\u8bc6\u522b\u56fe\u50cf\u4e2d\u7684\u6587\u5b57\uff0c\u9002\u5408\u7528\u4e8e\u9a8c\u8bc1\u7801\u7684\u8bc6\u522b\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u9a8c\u8bc1\u7801\u8bc6\u522b\u4e2d\u7684\u6311\u6218\uff0c\u6bd4\u5982\u626d\u66f2\u6216\u6a21\u7cca\u7684\u56fe\u50cf\uff1f<\/strong><br \/>\u5904\u7406\u9a8c\u8bc1\u7801\u8bc6\u522b\u4e2d\u7684\u6311\u6218\u901a\u5e38\u9700\u8981\u56fe\u50cf\u9884\u5904\u7406\u6280\u672f\u3002\u53ef\u4ee5\u5e94\u7528\u56fe\u50cf\u6ee4\u6ce2\u3001\u4e8c\u503c\u5316\u548c\u8f6e\u5ed3\u68c0\u6d4b\u7b49\u6280\u672f\u6765\u6539\u5584\u9a8c\u8bc1\u7801\u7684\u6e05\u6670\u5ea6\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u8bad\u7ec3\u81ea\u5b9a\u4e49\u8bc6\u522b\u5668\u4e5f\u662f\u4e00\u79cd\u6709\u6548\u7684\u65b9\u5f0f\uff0c\u5c24\u5176\u662f\u5bf9\u4e8e\u590d\u6742\u6216\u5177\u6709\u5e72\u6270\u80cc\u666f\u7684\u9a8c\u8bc1\u7801\u3002\u5bf9\u4e8e\u7279\u5b9a\u7c7b\u578b\u7684\u9a8c\u8bc1\u7801\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u4e13\u95e8\u7684\u8bc6\u522b\u670d\u52a1\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python3\u83b7\u53d6\u9a8c\u8bc1\u7801\u7684\u65b9\u6cd5\u5305\u62ecrequests\u5e93\u3001BeautifulSoup\u5e93\u3001pytesseract\u5e93\u3001 [&hellip;]","protected":false},"author":3,"featured_media":1067107,"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\/1067101"}],"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=1067101"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1067101\/revisions"}],"predecessor-version":[{"id":1067110,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1067101\/revisions\/1067110"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1067107"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1067101"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1067101"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1067101"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}