{"id":1052910,"date":"2024-12-31T14:29:16","date_gmt":"2024-12-31T06:29:16","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1052910.html"},"modified":"2024-12-31T14:29:19","modified_gmt":"2024-12-31T06:29:19","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e4%b8%8b%e8%bd%bd%e7%bd%91%e9%a1%b5%e5%9b%be%e7%89%87%e5%a4%a7%e5%b0%8f","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1052910.html","title":{"rendered":"\u5982\u4f55\u7528python\u4e0b\u8f7d\u7f51\u9875\u56fe\u7247\u5927\u5c0f"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/b989344a-175a-4a6a-b270-83ecf60c28e2.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"\u5982\u4f55\u7528python\u4e0b\u8f7d\u7f51\u9875\u56fe\u7247\u5927\u5c0f\" \/><\/p>\n<p><p> <strong>\u5728Python\u4e2d\uff0c\u4f7f\u7528\u5e93\u5982requests\u548cBeautifulSoup\u4e0b\u8f7d\u7f51\u9875\u56fe\u7247\u5927\u5c0f\u7684\u6b65\u9aa4\u5982\u4e0b<\/strong>\uff1a1. \u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c2. \u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875HTML\uff0c3. \u67e5\u627e\u5e76\u63d0\u53d6\u6240\u6709\u56fe\u7247\u94fe\u63a5\uff0c4. \u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u56fe\u7247\uff0c5. \u83b7\u53d6\u56fe\u7247\u7684\u5927\u5c0f\u3002<strong>\u5176\u4e2d\uff0c\u83b7\u53d6\u56fe\u7247\u5927\u5c0f\u7684\u65b9\u6cd5\u4e3b\u8981\u6709\u4e24\u79cd\uff1a\u76f4\u63a5\u4ece\u4e0b\u8f7d\u7684\u56fe\u7247\u6587\u4ef6\u4e2d\u83b7\u53d6\u3001\u4f7f\u7528HTTP\u8bf7\u6c42\u7684Content-Length\u5934\u4fe1\u606f<\/strong>\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u5b89\u88c5\u5fc5\u8981\u7684\u5e93<\/h3>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u786e\u4fdd\u5df2\u5b89\u88c5\u6240\u9700\u7684Python\u5e93\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528pip\u5b89\u88c5\u8fd9\u4e9b\u5e93\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><h3>\u4e8c\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u8fd9\u4e00\u6b65\u9aa4\u662f\u6240\u6709\u540e\u7eed\u64cd\u4f5c\u7684\u57fa\u7840\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875HTML<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790\u7f51\u9875HTML\uff0c\u4ee5\u4fbf\u63d0\u53d6\u6240\u6709\u56fe\u7247\u94fe\u63a5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>images = soup.find_all(&#39;img&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u63d0\u53d6\u56fe\u7247\u94fe\u63a5\u5e76\u4e0b\u8f7d\u56fe\u7247<\/h3>\n<\/p>\n<p><p>\u63d0\u53d6\u6bcf\u4e2a<img>\u6807\u7b7e\u7684src\u5c5e\u6027\uff0c\u8fd9\u662f\u56fe\u7247\u7684URL\u3002\u7136\u540e\uff0c\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u6bcf\u5f20\u56fe\u7247\uff0c\u5e76\u83b7\u53d6\u5176\u5927\u5c0f\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import os<\/p>\n<p>image_urls = [img[&#39;src&#39;] for img in images]<\/p>\n<p>download_folder = &#39;downloaded_images&#39;<\/p>\n<p>if not os.path.exists(download_folder):<\/p>\n<p>    os.makedirs(download_folder)<\/p>\n<p>for i, image_url in enumerate(image_urls):<\/p>\n<p>    image_response = requests.get(image_url, stream=True)<\/p>\n<p>    image_path = os.path.join(download_folder, f&#39;image_{i}.jpg&#39;)<\/p>\n<p>    with open(image_path, &#39;wb&#39;) as file:<\/p>\n<p>        for chunk in image_response.iter_content(1024):<\/p>\n<p>            file.write(chunk)<\/p>\n<p>    # \u83b7\u53d6\u56fe\u7247\u5927\u5c0f<\/p>\n<p>    image_size = os.path.getsize(image_path)<\/p>\n<p>    print(f&#39;Image {i} size: {image_size} bytes&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u4f7f\u7528HTTP\u8bf7\u6c42\u7684Content-Length\u5934\u4fe1\u606f<\/h3>\n<\/p>\n<p><p>\u53e6\u4e00\u79cd\u83b7\u53d6\u56fe\u7247\u5927\u5c0f\u7684\u65b9\u6cd5\u662f\u4f7f\u7528HTTP\u8bf7\u6c42\u7684Content-Length\u5934\u4fe1\u606f\u3002\u8fd9\u6837\u53ef\u4ee5\u907f\u514d\u4e0b\u8f7d\u6574\u4e2a\u56fe\u7247\u6587\u4ef6\uff0c\u53ea\u9700\u53d1\u9001\u4e00\u4e2aHEAD\u8bf7\u6c42\u5373\u53ef\u83b7\u53d6\u56fe\u7247\u5927\u5c0f\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for i, image_url in enumerate(image_urls):<\/p>\n<p>    image_response = requests.head(image_url)<\/p>\n<p>    image_size = image_response.headers.get(&#39;Content-Length&#39;)<\/p>\n<p>    if image_size:<\/p>\n<p>        print(f&#39;Image {i} size: {image_size} bytes&#39;)<\/p>\n<p>    else:<\/p>\n<p>        print(f&#39;Image {i} size could not be determined&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u5904\u7406\u76f8\u5bf9\u8def\u5f84\u7684\u56fe\u7247\u94fe\u63a5<\/h3>\n<\/p>\n<p><p>\u6709\u65f6\uff0c\u56fe\u7247\u94fe\u63a5\u53ef\u80fd\u662f\u76f8\u5bf9\u8def\u5f84\u800c\u4e0d\u662f\u7edd\u5bf9\u8def\u5f84\u3002\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u9700\u8981\u5c06\u76f8\u5bf9\u8def\u5f84\u8f6c\u6362\u4e3a\u7edd\u5bf9\u8def\u5f84\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from urllib.parse import urljoin<\/p>\n<p>image_urls = [urljoin(url, img[&#39;src&#39;]) for img in images]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e03\u3001\u5904\u7406\u5f02\u5e38\u60c5\u51b5<\/h3>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u5f02\u5e38\u60c5\u51b5\uff0c\u4f8b\u5982\u7f51\u7edc\u9519\u8bef\u3001\u65e0\u6548URL\u7b49\u3002\u56e0\u6b64\uff0c\u9700\u8981\u6dfb\u52a0\u5f02\u5e38\u5904\u7406\u4ee3\u7801\u4ee5\u786e\u4fdd\u7a0b\u5e8f\u7684\u5065\u58ee\u6027\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for i, image_url in enumerate(image_urls):<\/p>\n<p>    try:<\/p>\n<p>        image_response = requests.head(image_url)<\/p>\n<p>        image_size = image_response.headers.get(&#39;Content-Length&#39;)<\/p>\n<p>        if image_size:<\/p>\n<p>            print(f&#39;Image {i} size: {image_size} bytes&#39;)<\/p>\n<p>        else:<\/p>\n<p>            print(f&#39;Image {i} size could not be determined&#39;)<\/p>\n<p>    except requests.RequestException as e:<\/p>\n<p>        print(f&#39;F<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led to retrieve image {i}: {e}&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516b\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528Python\u4e0b\u8f7d\u7f51\u9875\u56fe\u7247\u5927\u5c0f\u7684\u8fc7\u7a0b\u5305\u62ec\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u89e3\u6790HTML\u3001\u63d0\u53d6\u56fe\u7247\u94fe\u63a5\u3001\u4e0b\u8f7d\u56fe\u7247\u4ee5\u53ca\u83b7\u53d6\u56fe\u7247\u5927\u5c0f\u3002\u901a\u8fc7requests\u548cBeautifulSoup\u5e93\uff0c\u53ef\u4ee5\u8f7b\u677e\u5b9e\u73b0\u8fd9\u4e00\u8fc7\u7a0b\u3002<strong>\u83b7\u53d6\u56fe\u7247\u5927\u5c0f\u7684\u65b9\u6cd5\u4e3b\u8981\u6709\u76f4\u63a5\u4ece\u4e0b\u8f7d\u7684\u56fe\u7247\u6587\u4ef6\u4e2d\u83b7\u53d6\u3001\u4f7f\u7528HTTP\u8bf7\u6c42\u7684Content-Length\u5934\u4fe1\u606f<\/strong>\uff0c\u6839\u636e\u5b9e\u9645\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u3002\u540c\u65f6\uff0c\u5904\u7406\u76f8\u5bf9\u8def\u5f84\u7684\u56fe\u7247\u94fe\u63a5\u548c\u5f02\u5e38\u60c5\u51b5\u4e5f\u662f\u5fc5\u4e0d\u53ef\u5c11\u7684\u6b65\u9aa4\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u4e0b\u8f7d\u7279\u5b9a\u5927\u5c0f\u7684\u7f51\u9875\u56fe\u7247\uff1f<\/strong><br \/>\u53ef\u4ee5\u4f7f\u7528Python\u4e2d\u7684requests\u5e93\u548cBeautifulSoup\u5e93\u6765\u4e0b\u8f7d\u7f51\u9875\u4e0a\u7684\u56fe\u7247\u3002\u9996\u5148\uff0c\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u5229\u7528BeautifulSoup\u89e3\u6790HTML\uff0c\u627e\u5230\u6240\u6709\u56fe\u7247\u7684\u94fe\u63a5\u3002\u63a5\u7740\uff0c\u53ef\u4ee5\u6839\u636e\u56fe\u7247\u7684\u5927\u5c0f\u7b5b\u9009\u51fa\u7b26\u5408\u6761\u4ef6\u7684\u56fe\u7247\u8fdb\u884c\u4e0b\u8f7d\u3002\u5177\u4f53\u7684\u4ee3\u7801\u793a\u4f8b\u53ef\u4ee5\u53c2\u8003\u5982\u4e0b\uff1a<\/p>\n<pre><code class=\"language-python\">import requests\nfrom bs4 import BeautifulSoup\nfrom PIL import Image\nfrom io import BytesIO\n\nurl = &#39;\u4f60\u7684\u7f51\u9875\u94fe\u63a5&#39;\nresponse = requests.get(url)\nsoup = BeautifulSoup(response.text, &#39;html.parser&#39;)\n\nfor img in soup.find_all(&#39;img&#39;):\n    img_url = img.get(&#39;src&#39;)\n    img_response = requests.get(img_url)\n    img_data = Image.open(BytesIO(img_response.content))\n    \n    if img_data.size[0] &gt; 100 and img_data.size[1] &gt; 100:  # \u6839\u636e\u9700\u8981\u7684\u5927\u5c0f\u8fdb\u884c\u7b5b\u9009\n        with open(&#39;\u4e0b\u8f7d\u7684\u56fe\u7247.jpg&#39;, &#39;wb&#39;) as f:\n            f.write(img_response.content)\n<\/code><\/pre>\n<p><strong>\u4f7f\u7528Python\u4e0b\u8f7d\u56fe\u7247\u65f6\u5982\u4f55\u5224\u65ad\u56fe\u7247\u5927\u5c0f\uff1f<\/strong><br \/>\u5728\u4e0b\u8f7d\u56fe\u7247\u4e4b\u524d\uff0c\u53ef\u4ee5\u4f7f\u7528PIL\u5e93\u4e2d\u7684Image\u6a21\u5757\u6765\u6253\u5f00\u56fe\u7247\uff0c\u5e76\u83b7\u53d6\u5176\u5927\u5c0f\u3002\u4f7f\u7528<code>Image.open()<\/code>\u65b9\u6cd5\u53ef\u4ee5\u52a0\u8f7d\u56fe\u7247\uff0c\u63a5\u7740\u901a\u8fc7<code>img.size<\/code>\u5c5e\u6027\u83b7\u53d6\u56fe\u7247\u7684\u5bbd\u5ea6\u548c\u9ad8\u5ea6\uff0c\u5224\u65ad\u662f\u5426\u7b26\u5408\u6307\u5b9a\u7684\u5927\u5c0f\u6761\u4ef6\u3002<\/p>\n<p><strong>\u4e0b\u8f7d\u7f51\u9875\u56fe\u7247\u65f6\u9700\u8981\u6ce8\u610f\u4ec0\u4e48\uff1f<\/strong><br \/>\u5728\u4e0b\u8f7d\u7f51\u9875\u56fe\u7247\u65f6\uff0c\u8981\u6ce8\u610f\u9075\u5b88\u7f51\u7ad9\u7684\u4f7f\u7528\u534f\u8bae\uff0c\u786e\u4fdd\u4f60\u6709\u6743\u4e0b\u8f7d\u548c\u4f7f\u7528\u8fd9\u4e9b\u56fe\u7247\u3002\u6b64\u5916\uff0c\u67d0\u4e9b\u7f51\u7ad9\u53ef\u80fd\u4f1a\u4f7f\u7528\u53cd\u722c\u866b\u6280\u672f\uff0c\u963b\u6b62\u81ea\u52a8\u5316\u8bf7\u6c42\uff0c\u56e0\u6b64\u9700\u8981\u8003\u8651\u4f7f\u7528\u5408\u9002\u7684\u8bf7\u6c42\u5934\u548c\u5904\u7406\u5f02\u5e38\u60c5\u51b5\u3002\u540c\u65f6\uff0c\u786e\u4fdd\u5904\u7406\u4e0b\u8f7d\u7684\u56fe\u7247\u65f6\u4f7f\u7528\u4e86\u9002\u5f53\u7684\u6587\u4ef6\u683c\u5f0f\u548c\u547d\u540d\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\uff0c\u4f7f\u7528\u5e93\u5982requests\u548cBeautifulSoup\u4e0b\u8f7d\u7f51\u9875\u56fe\u7247\u5927\u5c0f\u7684\u6b65\u9aa4\u5982\u4e0b\uff1a1. \u4f7f\u7528r [&hellip;]","protected":false},"author":3,"featured_media":1052923,"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\/1052910"}],"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=1052910"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1052910\/revisions"}],"predecessor-version":[{"id":1052926,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1052910\/revisions\/1052926"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1052923"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1052910"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1052910"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1052910"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}