{"id":1095028,"date":"2025-01-08T14:46:58","date_gmt":"2025-01-08T06:46:58","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1095028.html"},"modified":"2025-01-08T14:47:01","modified_gmt":"2025-01-08T06:47:01","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e5%81%9a%e9%85%b7%e7%8b%97%e9%9f%b3%e4%b9%90%e7%88%ac%e8%99%ab-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1095028.html","title":{"rendered":"\u5982\u4f55\u7528python\u505a\u9177\u72d7\u97f3\u4e50\u722c\u866b"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24210852\/371ad816-00d6-442e-b9bb-b8f7f10b655a.webp\" alt=\"\u5982\u4f55\u7528python\u505a\u9177\u72d7\u97f3\u4e50\u722c\u866b\" \/><\/p>\n<p><p> <strong>\u4f7f\u7528Python\u505a\u9177\u72d7\u97f3\u4e50\u722c\u866b\uff0c\u53ef\u4ee5\u901a\u8fc7\u89e3\u6790\u9177\u72d7\u97f3\u4e50\u7f51\u9875\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790\u54cd\u5e94\u6570\u636e\u6765\u83b7\u53d6\u76ee\u6807\u4fe1\u606f\u3001\u5904\u7406\u5e76\u5b58\u50a8\u6570\u636e\u7b49\u6b65\u9aa4\u6765\u5b9e\u73b0\u3002\u901a\u8fc7requests\u5e93\u53d1\u9001\u8bf7\u6c42\u3001BeautifulSoup\u89e3\u6790HTML\u3001\u4ee5\u53capandas\u5e93\u5904\u7406\u6570\u636e\u3002\u8be6\u7ec6\u6b65\u9aa4\u5982\u4e0b\uff1a<\/strong><\/p>\n<\/p>\n<p><p>\u4e00\u3001\u73af\u5883\u51c6\u5907<\/p>\n<\/p>\n<p><p>\u5f00\u59cb\u4e4b\u524d\uff0c\u9700\u8981\u786e\u4fdd\u5b89\u88c5\u4e86requests\u3001BeautifulSoup4\u3001pandas\u7b49\u5e93\u3002\u53ef\u4ee5\u901a\u8fc7pip\u5b89\u88c5\u8fd9\u4e9b\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install requests<\/p>\n<p>pip install beautifulsoup4<\/p>\n<p>pip install pandas<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e8c\u3001\u53d1\u9001HTTP\u8bf7\u6c42<\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5411\u9177\u72d7\u97f3\u4e50\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u9875\u9762\u5185\u5bb9\u3002\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u6765\u5b8c\u6210\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/www.kugou.com\/yy\/rank\/home\/1-8888.html?from=rank&#39;<\/p>\n<p>headers = {<\/p>\n<p>    &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u91cc\uff0c\u6211\u4eec\u6307\u5b9a\u4e86\u4e00\u4e2aURL\uff0c\u5e76\u4f2a\u88c5\u6210\u6d4f\u89c8\u5668\u53d1\u9001\u8bf7\u6c42\u3002\u901a\u8fc7\u8bbe\u7f6eheaders\uff0c\u6211\u4eec\u53ef\u4ee5\u907f\u514d\u8bf7\u6c42\u88ab\u62d2\u7edd\u3002<\/p>\n<\/p>\n<p><p>\u4e09\u3001\u89e3\u6790HTML<\/p>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u9700\u8981\u89e3\u6790\u83b7\u53d6\u5230\u7684\u9875\u9762\u5185\u5bb9\uff0c\u63d0\u53d6\u51fa\u6211\u4eec\u9700\u8981\u7684\u4fe1\u606f\u3002\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u6765\u5b8c\u6210\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u56db\u3001\u63d0\u53d6\u6570\u636e<\/p>\n<\/p>\n<p><p>\u5728\u83b7\u53d6\u5230\u89e3\u6790\u540e\u7684HTML\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u5206\u6790HTML\u7ed3\u6784\uff0c\u627e\u5230\u6211\u4eec\u9700\u8981\u7684\u97f3\u4e50\u4fe1\u606f\u3002\u4f8b\u5982\uff0c\u6211\u4eec\u53ef\u4ee5\u63d0\u53d6\u6b4c\u66f2\u540d\u548c\u6b4c\u624b\u540d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">songs = soup.find_all(&#39;div&#39;, class_=&#39;pc_temp_songname&#39;)<\/p>\n<p>for song in songs:<\/p>\n<p>    song_name = song.get_text().strip().split(&#39;-&#39;)[1].strip()<\/p>\n<p>    singer_name = song.get_text().strip().split(&#39;-&#39;)[0].strip()<\/p>\n<p>    print(f&#39;Song: {song_name}, Singer: {singer_name}&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u91cc\u6211\u4eec\u901a\u8fc7find_all\u65b9\u6cd5\u67e5\u627e\u6240\u6709\u5305\u542b\u6b4c\u66f2\u4fe1\u606f\u7684div\u6807\u7b7e\uff0c\u5e76\u63d0\u53d6\u5176\u4e2d\u7684\u6b4c\u66f2\u540d\u548c\u6b4c\u624b\u540d\u3002<\/p>\n<\/p>\n<p><p>\u4e94\u3001\u5904\u7406\u5e76\u5b58\u50a8\u6570\u636e<\/p>\n<\/p>\n<p><p>\u6700\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5c06\u63d0\u53d6\u5230\u7684\u6570\u636e\u5b58\u50a8\u5230\u4e00\u4e2aCSV\u6587\u4ef6\u4e2d\uff0c\u65b9\u4fbf\u540e\u7eed\u5904\u7406\u548c\u5206\u6790\u3002\u53ef\u4ee5\u4f7f\u7528pandas\u5e93\u6765\u5b8c\u6210\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<p>data = []<\/p>\n<p>songs = soup.find_all(&#39;div&#39;, class_=&#39;pc_temp_songname&#39;)<\/p>\n<p>for song in songs:<\/p>\n<p>    song_name = song.get_text().strip().split(&#39;-&#39;)[1].strip()<\/p>\n<p>    singer_name = song.get_text().strip().split(&#39;-&#39;)[0].strip()<\/p>\n<p>    data.append([song_name, singer_name])<\/p>\n<p>df = pd.DataFrame(data, columns=[&#39;Song&#39;, &#39;Singer&#39;])<\/p>\n<p>df.to_csv(&#39;kugou_songs.csv&#39;, index=False, encoding=&#39;utf-8&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u91cc\u6211\u4eec\u5c06\u63d0\u53d6\u5230\u7684\u6570\u636e\u5b58\u50a8\u5230\u4e00\u4e2aDataFrame\u4e2d\uff0c\u5e76\u5c06\u5176\u4fdd\u5b58\u4e3aCSV\u6587\u4ef6\u3002<\/p>\n<\/p>\n<p><p>\u516d\u3001\u5904\u7406\u5206\u9875<\/p>\n<\/p>\n<p><p>\u9177\u72d7\u97f3\u4e50\u7684\u6392\u884c\u699c\u9875\u9762\u901a\u5e38\u4f1a\u6709\u5206\u9875\u3002\u4e3a\u4e86\u83b7\u53d6\u66f4\u591a\u7684\u6570\u636e\uff0c\u6211\u4eec\u9700\u8981\u5904\u7406\u5206\u9875\u8bf7\u6c42\u3002\u53ef\u4ee5\u901a\u8fc7\u5206\u6790\u5206\u9875URL\u7684\u89c4\u5f8b\uff0c\u9010\u9875\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>import pandas as pd<\/p>\n<p>base_url = &#39;https:\/\/www.kugou.com\/yy\/rank\/home\/1-8888.html?from=rank&amp;page=&#39;<\/p>\n<p>headers = {<\/p>\n<p>    &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36&#39;<\/p>\n<p>}<\/p>\n<p>data = []<\/p>\n<p>for page in range(1, 11):  # \u5047\u8bbe\u670910\u9875\u6570\u636e<\/p>\n<p>    url = base_url + str(page)<\/p>\n<p>    response = requests.get(url, headers=headers)<\/p>\n<p>    soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p>    songs = soup.find_all(&#39;div&#39;, class_=&#39;pc_temp_songname&#39;)<\/p>\n<p>    for song in songs:<\/p>\n<p>        song_name = song.get_text().strip().split(&#39;-&#39;)[1].strip()<\/p>\n<p>        singer_name = song.get_text().strip().split(&#39;-&#39;)[0].strip()<\/p>\n<p>        data.append([song_name, singer_name])<\/p>\n<p>df = pd.DataFrame(data, columns=[&#39;Song&#39;, &#39;Singer&#39;])<\/p>\n<p>df.to_csv(&#39;kugou_songs.csv&#39;, index=False, encoding=&#39;utf-8&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e03\u3001\u5904\u7406\u53cd\u722c<\/p>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u722c\u866b\u64cd\u4f5c\u65f6\uff0c\u6211\u4eec\u53ef\u80fd\u4f1a\u9047\u5230\u53cd\u722c\u63aa\u65bd\u3002\u4e3a\u4e86\u5e94\u5bf9\u53cd\u722c\uff0c\u6211\u4eec\u53ef\u4ee5\u91c7\u53d6\u4e00\u4e9b\u63aa\u65bd\uff0c\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<ol>\n<li><strong>\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/strong>\uff1a\u4f2a\u88c5\u6210\u6d4f\u89c8\u5668\uff0c\u907f\u514d\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u3002<\/li>\n<li><strong>\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694<\/strong>\uff1a\u5728\u6bcf\u6b21\u8bf7\u6c42\u4e4b\u95f4\u6dfb\u52a0\u968f\u673a\u7684\u5ef6\u8fdf\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u3002<\/li>\n<li><strong>\u4f7f\u7528\u4ee3\u7406<\/strong>\uff1a\u901a\u8fc7\u4ee3\u7406\u670d\u52a1\u5668\u53d1\u9001\u8bf7\u6c42\uff0c\u907f\u514dIP\u88ab\u5c01\u7981\u3002<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">import time<\/p>\n<p>import random<\/p>\n<p>for page in range(1, 11):<\/p>\n<p>    url = base_url + str(page)<\/p>\n<p>    response = requests.get(url, headers=headers)<\/p>\n<p>    soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p>    songs = soup.find_all(&#39;div&#39;, class_=&#39;pc_temp_songname&#39;)<\/p>\n<p>    for song in songs:<\/p>\n<p>        song_name = song.get_text().strip().split(&#39;-&#39;)[1].strip()<\/p>\n<p>        singer_name = song.get_text().strip().split(&#39;-&#39;)[0].strip()<\/p>\n<p>        data.append([song_name, singer_name])<\/p>\n<p>    time.sleep(random.uniform(1, 3))  # \u968f\u673a\u5ef6\u8fdf1\u52303\u79d2<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e9b\u63aa\u65bd\uff0c\u53ef\u4ee5\u63d0\u9ad8\u722c\u866b\u7684\u7a33\u5b9a\u6027\uff0c\u907f\u514d\u88ab\u53cd\u722c\u673a\u5236\u963b\u6321\u3002<\/p>\n<\/p>\n<p><p>\u516b\u3001\u603b\u7ed3<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u5b9e\u73b0\u4e00\u4e2a\u7b80\u5355\u7684\u9177\u72d7\u97f3\u4e50\u722c\u866b\u3002\u6211\u4eec\u9996\u5148\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u9875\u9762\u5185\u5bb9\uff0c\u7136\u540e\u89e3\u6790HTML\uff0c\u63d0\u53d6\u6240\u9700\u6570\u636e\uff0c\u6700\u540e\u5904\u7406\u5e76\u5b58\u50a8\u6570\u636e\u3002\u4e3a\u4e86\u5e94\u5bf9\u53cd\u722c\u63aa\u65bd\uff0c\u6211\u4eec\u53ef\u4ee5\u8bbe\u7f6e\u8bf7\u6c42\u5934\u3001\u8bf7\u6c42\u95f4\u9694\u548c\u4f7f\u7528\u4ee3\u7406\u3002\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\uff0c\u6211\u4eec\u53ef\u4ee5\u83b7\u53d6\u5230\u9177\u72d7\u97f3\u4e50\u6392\u884c\u699c\u4e0a\u7684\u6b4c\u66f2\u4fe1\u606f\uff0c\u8fdb\u884c\u540e\u7eed\u5206\u6790\u548c\u5904\u7406\u3002<\/p>\n<\/p>\n<p><p>\u8fd9\u53ea\u662f\u4e00\u4e2a\u57fa\u7840\u7684\u722c\u866b\u793a\u4f8b\uff0c\u5b9e\u9645\u5e94\u7528\u4e2d\u53ef\u80fd\u4f1a\u9047\u5230\u66f4\u591a\u7684\u590d\u6742\u60c5\u51b5\uff0c\u4f8b\u5982\u9700\u8981\u5904\u7406JavaScript\u6e32\u67d3\u7684\u9875\u9762\u3001\u9700\u8981\u6a21\u62df\u7528\u6237\u767b\u5f55\u7b49\u3002\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u8fdb\u884c\u76f8\u5e94\u7684\u8c03\u6574\u548c\u4f18\u5316\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u5f00\u59cb\u4f7f\u7528Python\u8fdb\u884c\u9177\u72d7\u97f3\u4e50\u6570\u636e\u7684\u722c\u53d6\uff1f<\/strong><br \/>\u8981\u5f00\u59cb\u4f7f\u7528Python\u722c\u53d6\u9177\u72d7\u97f3\u4e50\u6570\u636e\uff0c\u60a8\u9700\u8981\u5b89\u88c5\u4e00\u4e9b\u57fa\u672c\u7684\u5e93\uff0c\u5982Requests\u548cBeautifulSoup\u3002Requests\u5e93\u5e2e\u52a9\u60a8\u53d1\u9001\u7f51\u7edc\u8bf7\u6c42\u4ee5\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u800cBeautifulSoup\u5219\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\u3002\u5b89\u88c5\u8fd9\u4e24\u4e2a\u5e93\u540e\uff0c\u60a8\u53ef\u4ee5\u901a\u8fc7\u5206\u6790\u9177\u72d7\u97f3\u4e50\u7684\u7f51\u9875\u7ed3\u6784\uff0c\u786e\u5b9a\u9700\u8981\u63d0\u53d6\u7684\u5143\u7d20\uff0c\u4f8b\u5982\u6b4c\u66f2\u6807\u9898\u3001\u827a\u672f\u5bb6\u540d\u548c\u4e13\u8f91\u4fe1\u606f\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u9177\u72d7\u97f3\u4e50\u65f6\uff0c\u6709\u54ea\u4e9b\u5e38\u89c1\u7684\u53cd\u722c\u866b\u673a\u5236\u9700\u8981\u6ce8\u610f\uff1f<\/strong><br \/>\u9177\u72d7\u97f3\u4e50\u53ef\u80fd\u4f1a\u91c7\u53d6\u4e00\u4e9b\u53cd\u722c\u866b\u63aa\u65bd\uff0c\u6bd4\u5982IP\u9650\u5236\u3001\u8bf7\u6c42\u9891\u7387\u9650\u5236\u548c\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u7b49\u3002\u4e3a\u4e86\u5e94\u5bf9\u8fd9\u4e9b\u63aa\u65bd\uff0c\u5efa\u8bae\u60a8\u8bbe\u7f6e\u9002\u5f53\u7684\u8bf7\u6c42\u95f4\u9694\uff0c\u4f7f\u7528\u4ee3\u7406IP\u548cUser-Agent\u4f2a\u88c5\uff0c\u786e\u4fdd\u60a8\u7684\u722c\u866b\u884c\u4e3a\u4e0d\u88ab\u8bc6\u522b\u3002\u540c\u65f6\uff0c\u6ce8\u610f\u9075\u5b88\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\uff0c\u786e\u4fdd\u60a8\u7684\u722c\u53d6\u884c\u4e3a\u5408\u6cd5\u5408\u89c4\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u83b7\u53d6\u5230\u7684\u9177\u72d7\u97f3\u4e50\u6570\u636e\uff1f<\/strong><br \/>\u5728\u6210\u529f\u722c\u53d6\u9177\u72d7\u97f3\u4e50\u6570\u636e\u540e\uff0c\u60a8\u53ef\u80fd\u5e0c\u671b\u5c06\u6570\u636e\u8fdb\u884c\u5b58\u50a8\u548c\u5904\u7406\u3002\u53ef\u4ee5\u9009\u62e9\u5c06\u6570\u636e\u4fdd\u5b58\u5230CSV\u6587\u4ef6\u3001\u6570\u636e\u5e93\u6216JSON\u683c\u5f0f\uff0c\u4ee5\u4fbf\u540e\u7eed\u5206\u6790\u548c\u4f7f\u7528\u3002\u4f7f\u7528Pandas\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u5904\u7406\u548c\u5206\u6790\u6570\u636e\uff0c\u60a8\u53ef\u4ee5\u8fdb\u884c\u6570\u636e\u6e05\u6d17\u3001\u53bb\u91cd\u548c\u53ef\u89c6\u5316\uff0c\u5e2e\u52a9\u60a8\u66f4\u597d\u5730\u7406\u89e3\u97f3\u4e50\u6570\u636e\u7684\u8d8b\u52bf\u548c\u7279\u5f81\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u505a\u9177\u72d7\u97f3\u4e50\u722c\u866b\uff0c\u53ef\u4ee5\u901a\u8fc7\u89e3\u6790\u9177\u72d7\u97f3\u4e50\u7f51\u9875\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790\u54cd\u5e94\u6570\u636e\u6765\u83b7\u53d6\u76ee\u6807\u4fe1\u606f\u3001\u5904\u7406\u5e76 [&hellip;]","protected":false},"author":3,"featured_media":1095031,"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\/1095028"}],"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=1095028"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1095028\/revisions"}],"predecessor-version":[{"id":1095034,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1095028\/revisions\/1095034"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1095031"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1095028"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1095028"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1095028"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}