{"id":1169347,"date":"2025-01-15T16:09:27","date_gmt":"2025-01-15T08:09:27","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1169347.html"},"modified":"2025-01-15T16:09:30","modified_gmt":"2025-01-15T08:09:30","slug":"python%e5%a6%82%e4%bd%95%e8%8e%b7%e5%8f%96%e5%9b%be%e7%89%87%e7%bd%91%e5%9d%80","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1169347.html","title":{"rendered":"python\u5982\u4f55\u83b7\u53d6\u56fe\u7247\u7f51\u5740"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/26070340\/fc2b2302-dabd-4cca-8bb4-37bd86afc8f6.webp\" alt=\"python\u5982\u4f55\u83b7\u53d6\u56fe\u7247\u7f51\u5740\" \/><\/p>\n<p><p> <strong>Python\u83b7\u53d6\u56fe\u7247\u7f51\u5740\u7684\u65b9\u6cd5\u6709\u5f88\u591a\u79cd\uff0c\u5e38\u89c1\u7684\u6709\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u3001\u4f7f\u7528API\u3001\u6216\u901a\u8fc7\u89e3\u6790HTML\u7b49\u3002\u4ee5\u4e0b\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u4e09\u79cd\u5e38\u89c1\u7684\u65b9\u6cd5\uff1a\u4f7f\u7528requests\u5e93\u548cBeautifulSoup\u5e93\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u3001\u901a\u8fc7API\u63a5\u53e3\u83b7\u53d6\u56fe\u7247\u7f51\u5740\u3001\u4f7f\u7528Selenium\u5e93\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u3002<\/strong><\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u4f7f\u7528requests\u5e93\u548cBeautifulSoup\u5e93\u8fdb\u884c\u7f51\u9875\u722c\u53d6<\/h3>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5\u4f9d\u8d56\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5requests\u548cBeautifulSoup\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p>pip install beautifulsoup4<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u7f16\u5199\u722c\u866b\u4ee3\u7801<\/h4>\n<\/p>\n<p><p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\u4ee3\u7801\uff0c\u7528\u4e8e\u4ece\u4e00\u4e2a\u7f51\u9875\u4e2d\u83b7\u53d6\u56fe\u7247\u7684URL\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<h2><strong>\u76ee\u6807\u7f51\u9875URL<\/strong><\/h2>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<h2><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>response = requests.get(url)<\/p>\n<p>if response.status_code == 200:<\/p>\n<p>    # \u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/p>\n<p>    soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p>    # \u67e5\u627e\u6240\u6709\u56fe\u7247\u6807\u7b7e<\/p>\n<p>    img_tags = soup.find_all(&#39;img&#39;)<\/p>\n<p>    # \u63d0\u53d6\u56fe\u7247URL<\/p>\n<p>    img_urls = [img[&#39;src&#39;] for img in img_tags]<\/p>\n<p>    for img_url in img_urls:<\/p>\n<p>        print(img_url)<\/p>\n<p>else:<\/p>\n<p>    print(f&quot;F<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led to retrieve webpage. Status code: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u901a\u8fc7API\u63a5\u53e3\u83b7\u53d6\u56fe\u7247\u7f51\u5740<\/h3>\n<\/p>\n<p><h4>1\u3001\u4f7f\u7528Pexels API\u83b7\u53d6\u56fe\u7247URL<\/h4>\n<\/p>\n<p><p>Pexels\u662f\u4e00\u4e2a\u63d0\u4f9b\u9ad8\u8d28\u91cf\u514d\u8d39\u7167\u7247\u548c\u89c6\u9891\u7684\u5e73\u53f0\u3002\u4f60\u53ef\u4ee5\u901a\u8fc7Pexels API\u83b7\u53d6\u56fe\u7247\u7684URL\u3002\u9996\u5148\uff0c\u4f60\u9700\u8981\u6ce8\u518c\u4e00\u4e2aPexels\u8d26\u53f7\u5e76\u83b7\u53d6API\u5bc6\u94a5\u3002<\/p>\n<\/p>\n<p><h4>2\u3001\u7f16\u5199\u4ee3\u7801<\/h4>\n<\/p>\n<p><p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528Pexels API\u83b7\u53d6\u56fe\u7247URL\u7684\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>Pexels API\u5bc6\u94a5<\/strong><\/h2>\n<p>api_key = &#39;YOUR_API_KEY&#39;<\/p>\n<h2><strong>\u76ee\u6807URL<\/strong><\/h2>\n<p>url = &#39;https:\/\/api.pexels.com\/v1\/search&#39;<\/p>\n<h2><strong>\u67e5\u8be2\u53c2\u6570<\/strong><\/h2>\n<p>params = {<\/p>\n<p>    &#39;query&#39;: &#39;nature&#39;,<\/p>\n<p>    &#39;per_page&#39;: 10,<\/p>\n<p>}<\/p>\n<h2><strong>\u8bf7\u6c42\u5934<\/strong><\/h2>\n<p>headers = {<\/p>\n<p>    &#39;Authorization&#39;: api_key,<\/p>\n<p>}<\/p>\n<h2><strong>\u53d1\u9001\u8bf7\u6c42<\/strong><\/h2>\n<p>response = requests.get(url, headers=headers, params=params)<\/p>\n<p>if response.status_code == 200:<\/p>\n<p>    data = response.json()<\/p>\n<p>    for photo in data[&#39;photos&#39;]:<\/p>\n<p>        print(photo[&#39;src&#39;][&#39;original&#39;])<\/p>\n<p>else:<\/p>\n<p>    print(f&quot;Failed to retrieve images. Status code: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528Selenium\u5e93\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c<\/h3>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5\u4f9d\u8d56\u5e93<\/h4>\n<\/p>\n<p><p>\u4f60\u9700\u8981\u5b89\u88c5Selenium\u5e93\u548c\u6d4f\u89c8\u5668\u9a71\u52a8\uff08\u4f8b\u5982ChromeDriver\uff09\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5Selenium\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u7f16\u5199\u4ee3\u7801<\/h4>\n<\/p>\n<p><p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528Selenium\u83b7\u53d6\u56fe\u7247URL\u7684\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>from selenium.webdriver.common.by import By<\/p>\n<h2><strong>\u8bbe\u7f6e\u6d4f\u89c8\u5668\u9a71\u52a8\u8def\u5f84<\/strong><\/h2>\n<p>driver_path = &#39;\/path\/to\/chromedriver&#39;<\/p>\n<h2><strong>\u521b\u5efa\u6d4f\u89c8\u5668\u5bf9\u8c61<\/strong><\/h2>\n<p>driver = webdriver.Chrome(executable_path=driver_path)<\/p>\n<h2><strong>\u6253\u5f00\u76ee\u6807\u7f51\u9875<\/strong><\/h2>\n<p>driver.get(&#39;http:\/\/example.com&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u6240\u6709\u56fe\u7247\u6807\u7b7e<\/strong><\/h2>\n<p>img_tags = driver.find_elements(By.TAG_NAME, &#39;img&#39;)<\/p>\n<h2><strong>\u63d0\u53d6\u56fe\u7247URL<\/strong><\/h2>\n<p>img_urls = [img.get_attribute(&#39;src&#39;) for img in img_tags]<\/p>\n<p>for img_url in img_urls:<\/p>\n<p>    print(img_url)<\/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>\u56db\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u4e09\u79cd\u65b9\u6cd5\uff0c\u4f60\u53ef\u4ee5\u8f7b\u677e\u5730\u5728Python\u4e2d\u83b7\u53d6\u56fe\u7247\u7684URL\u3002<strong>\u4f7f\u7528requests\u548cBeautifulSoup\u5e93\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u7b80\u5355\u9ad8\u6548\uff0c\u9002\u7528\u4e8e\u9759\u6001\u7f51\u9875\uff1b\u901a\u8fc7API\u63a5\u53e3\u83b7\u53d6\u56fe\u7247URL\u53ef\u4ee5\u83b7\u5f97\u9ad8\u8d28\u91cf\u7684\u56fe\u7247\u8d44\u6e90\uff0c\u5982Pexels\u7b49\u5e73\u53f0\uff1b\u4f7f\u7528Selenium\u5e93\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u9002\u7528\u4e8e\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u7684\u7f51\u9875<\/strong>\u3002\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u53ef\u4ee5\u66f4\u52a0\u9ad8\u6548\u5730\u5b8c\u6210\u4efb\u52a1\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u56fe\u7247\u7f51\u5740\uff1f<\/strong><br \/>\u8981\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u56fe\u7247\u7f51\u5740\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684\u7f51\u7edc\u8bf7\u6c42\u5e93\uff08\u5982requests\uff09\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u5229\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u3002\u901a\u8fc7\u67e5\u627e\u6240\u6709\u7684<img>\u6807\u7b7e\uff0c\u53ef\u4ee5\u83b7\u53d6\u5230\u56fe\u7247\u7684src\u5c5e\u6027\uff0c\u4ece\u800c\u5f97\u5230\u56fe\u7247\u7f51\u5740\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a  <\/p>\n<pre><code class=\"language-python\">import requests\nfrom bs4 import BeautifulSoup\n\nurl = &#39;https:\/\/example.com&#39;\nresponse = requests.get(url)\nsoup = BeautifulSoup(response.text, &#39;html.parser&#39;)\nimages = soup.find_all(&#39;img&#39;)\nimage_urls = [img[&#39;src&#39;] for img in images if &#39;src&#39; in img.attrs]\nprint(image_urls)\n<\/code><\/pre>\n<p><strong>\u4f7f\u7528Python\u5982\u4f55\u4e0b\u8f7d\u7f51\u9875\u4e0a\u7684\u56fe\u7247\uff1f<\/strong><br \/>\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u7f51\u9875\u4e0a\u7684\u56fe\u7247\u3002\u83b7\u53d6\u56fe\u7247\u7f51\u5740\u540e\uff0c\u53ef\u4ee5\u518d\u6b21\u4f7f\u7528requests\u5e93\u53d1\u9001GET\u8bf7\u6c42\u6765\u4e0b\u8f7d\u56fe\u7247\u3002\u901a\u8fc7\u8bbe\u7f6e\u9002\u5f53\u7684\u6587\u4ef6\u540d\u548c\u6587\u4ef6\u8def\u5f84\uff0c\u53ef\u4ee5\u4fdd\u5b58\u56fe\u7247\u5230\u672c\u5730\u3002\u4ee5\u4e0b\u662f\u4e0b\u8f7d\u56fe\u7247\u7684\u793a\u4f8b\u4ee3\u7801\uff1a  <\/p>\n<pre><code class=\"language-python\">import requests\n\nimage_url = &#39;https:\/\/example.com\/image.jpg&#39;\nresponse = requests.get(image_url)\nif response.status_code == 200:\n    with open(&#39;image.jpg&#39;, &#39;wb&#39;) as file:\n        file.write(response.content)\n<\/code><\/pre>\n<p><strong>Python\u4e2d\u662f\u5426\u6709\u5e93\u53ef\u4ee5\u7b80\u5316\u56fe\u7247\u7f51\u5740\u7684\u63d0\u53d6\u8fc7\u7a0b\uff1f<\/strong><br \/>\u662f\u7684\uff0c\u9664\u4e86requests\u548cBeautifulSoup\uff0cPython\u8fd8\u53ef\u4ee5\u4f7f\u7528Scrapy\u6846\u67b6\u6765\u7b80\u5316\u7f51\u7edc\u722c\u866b\u7684\u8fc7\u7a0b\u3002Scrapy\u53ef\u4ee5\u8f7b\u677e\u5730\u6293\u53d6\u7f51\u9875\u5185\u5bb9\u5e76\u63d0\u53d6\u6240\u9700\u7684\u56fe\u7247\u7f51\u5740\uff0c\u9002\u5408\u5904\u7406\u66f4\u590d\u6742\u7684\u7f51\u7ad9\u7ed3\u6784\u548c\u5927\u89c4\u6a21\u7684\u6570\u636e\u6293\u53d6\u3002Scrapy\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u529f\u80fd\u548c\u7075\u6d3b\u7684\u914d\u7f6e\u9009\u9879\uff0c\u53ef\u4ee5\u66f4\u9ad8\u6548\u5730\u8fdb\u884c\u6570\u636e\u6293\u53d6\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u83b7\u53d6\u56fe\u7247\u7f51\u5740\u7684\u65b9\u6cd5\u6709\u5f88\u591a\u79cd\uff0c\u5e38\u89c1\u7684\u6709\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u3001\u4f7f\u7528API\u3001\u6216\u901a\u8fc7\u89e3\u6790HTML\u7b49\u3002\u4ee5\u4e0b\u5c06\u8be6\u7ec6\u4ecb\u7ecd [&hellip;]","protected":false},"author":3,"featured_media":1169354,"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\/1169347"}],"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=1169347"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1169347\/revisions"}],"predecessor-version":[{"id":1169355,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1169347\/revisions\/1169355"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1169354"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1169347"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1169347"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1169347"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}