{"id":1059558,"date":"2024-12-31T15:26:10","date_gmt":"2024-12-31T07:26:10","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1059558.html"},"modified":"2024-12-31T15:26:13","modified_gmt":"2024-12-31T07:26:13","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e9%80%9a%e8%bf%87%e4%ba%ba%e5%90%8d%e6%9f%a5%e5%8f%b7%e7%a0%81","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1059558.html","title":{"rendered":"\u5982\u4f55\u7528python\u901a\u8fc7\u4eba\u540d\u67e5\u53f7\u7801"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/52c6c9b3-e644-4cf0-ba26-62d28b615052.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"\u5982\u4f55\u7528python\u901a\u8fc7\u4eba\u540d\u67e5\u53f7\u7801\" \/><\/p>\n<p><p> <strong>\u5982\u4f55\u7528Python\u901a\u8fc7\u4eba\u540d\u67e5\u53f7\u7801<\/strong><\/p>\n<\/p>\n<p><p>\u8981\u4f7f\u7528Python\u901a\u8fc7\u4eba\u540d\u67e5\u627e\u7535\u8bdd\u53f7\u7801\uff0c<strong>\u53ef\u4ee5\u4f7f\u7528Web Scraping\u3001API\u8c03\u7528\u3001\u672c\u5730\u6570\u636e\u5e93\u67e5\u8be2<\/strong>\u7b49\u65b9\u6cd5\u6765\u5b9e\u73b0\u3002\u8fd9\u91cc\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u5229\u7528\u8fd9\u51e0\u79cd\u65b9\u6cd5\u5b9e\u73b0\u8fd9\u4e00\u76ee\u6807\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001WEB SCRAPING<\/h3>\n<\/p>\n<p><p>Web scraping\u662f\u4ece\u7f51\u7ad9\u4e0a\u63d0\u53d6\u6570\u636e\u7684\u8fc7\u7a0b\u3002\u5c3d\u7ba1\u8fd9\u79cd\u65b9\u6cd5\u6709\u4e00\u5b9a\u7684\u5c40\u9650\u6027\uff0c\u7279\u522b\u662f\u56e0\u4e3a\u4e00\u4e9b\u7f51\u7ad9\u7981\u6b62\u722c\u53d6\u6216\u6709\u53cd\u722c\u866b\u673a\u5236\uff0c\u4f46\u5b83\u4ecd\u7136\u662f\u83b7\u53d6\u516c\u5f00\u4fe1\u606f\u7684\u4e00\u79cd\u6709\u6548\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528BeautifulSoup\u8fdb\u884c\u7f51\u9875\u89e3\u6790<\/h4>\n<\/p>\n<p><p>BeautifulSoup\u662f\u4e00\u4e2aPython\u5e93\uff0c\u7528\u4e8e\u4eceHTML\u6216XML\u6587\u4ef6\u4e2d\u63d0\u53d6\u6570\u636e\u3002\u5b83\u521b\u5efa\u4e86\u4e00\u4e2a\u89e3\u6790\u6811\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u4eceHTML\u6216XML\u6587\u4ef6\u4e2d\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>import requests<\/p>\n<p>def get_phone_number(name):<\/p>\n<p>    url = f&quot;http:\/\/example.com\/search?name={name}&quot;<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p>    # \u5047\u8bbe\u7535\u8bdd\u53f7\u7801\u4f4d\u4e8e\u7279\u5b9a\u7684\u6807\u7b7e\u4e2d\uff0c\u5982&lt;div class=&quot;phone&quot;&gt;<\/p>\n<p>    phone_number = soup.find(&#39;div&#39;, class_=&#39;phone&#39;).text<\/p>\n<p>    return phone_number<\/p>\n<p>name = &quot;John Doe&quot;<\/p>\n<p>print(get_phone_number(name))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528<code>requests<\/code>\u5e93\u6765\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u5e76\u4f7f\u7528<code>BeautifulSoup<\/code>\u89e3\u6790\u8fd4\u56de\u7684HTML\u5185\u5bb9\uff0c\u7136\u540e\u63d0\u53d6\u7535\u8bdd\u53f7\u7801\u3002<\/p>\n<\/p>\n<p><h4>2. \u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h4>\n<\/p>\n<p><p>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u4f7f\u7528\u53cd\u722c\u866b\u673a\u5236\u6765\u9632\u6b62\u81ea\u52a8\u5316\u8bbf\u95ee\u3002\u5e38\u89c1\u7684\u53cd\u722c\u866b\u673a\u5236\u5305\u62ec\u4f7f\u7528CAPTCHA\u3001\u68c0\u6d4b\u8bbf\u95ee\u9891\u7387\u7b49\u3002\u4e3a\u4e86\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<ul>\n<li><strong>\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/strong>\uff1a\u6a21\u62df\u6d4f\u89c8\u5668\u8bbf\u95ee\u3002<\/li>\n<li><strong>\u4f7f\u7528\u4ee3\u7406<\/strong>\uff1a\u907f\u514d\u5355\u4e2aIP\u88ab\u5c01\u7981\u3002<\/li>\n<li><strong>\u8c03\u6574\u8bbf\u95ee\u9891\u7387<\/strong>\uff1a\u907f\u514d\u9891\u7e41\u8bbf\u95ee\u3002<\/li>\n<\/ul>\n<p><pre><code class=\"language-python\">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><h3>\u4e8c\u3001API\u8c03\u7528<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528API\u662f\u83b7\u53d6\u6570\u636e\u7684\u53e6\u4e00\u79cd\u6709\u6548\u65b9\u6cd5\u3002\u8bb8\u591a\u670d\u52a1\u63d0\u4f9b\u5546\u4f1a\u63d0\u4f9bAPI\u4f9b\u5f00\u53d1\u8005\u67e5\u8be2\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528\u516c\u5f00API<\/h4>\n<\/p>\n<p><p>\u5047\u8bbe\u6211\u4eec\u6709\u4e00\u4e2a\u7535\u8bdd\u53f7\u7801\u67e5\u8be2API\uff0c\u4ee5\u4e0b\u662f\u4f7f\u7528Python\u8c03\u7528API\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>def get_phone_number(name):<\/p>\n<p>    api_key = &quot;your_api_key&quot;<\/p>\n<p>    url = f&quot;https:\/\/api.example.com\/phone_lookup?name={name}&amp;api_key={api_key}&quot;<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    if response.status_code == 200:<\/p>\n<p>        data = response.json()<\/p>\n<p>        phone_number = data[&#39;phone_number&#39;]<\/p>\n<p>        return phone_number<\/p>\n<p>    else:<\/p>\n<p>        return None<\/p>\n<p>name = &quot;John Doe&quot;<\/p>\n<p>print(get_phone_number(name))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u53d1\u9001\u4e86\u4e00\u4e2aGET\u8bf7\u6c42\u5230API\uff0c\u5e76\u89e3\u6790\u4e86\u8fd4\u56de\u7684JSON\u6570\u636e\u6765\u83b7\u53d6\u7535\u8bdd\u53f7\u7801\u3002<\/p>\n<\/p>\n<p><h4>2. \u5904\u7406API\u9650\u5236<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528API\u65f6\uff0c\u901a\u5e38\u4f1a\u6709\u4f7f\u7528\u9650\u5236\uff0c\u5982\u6bcf\u5206\u949f\u7684\u8bf7\u6c42\u6b21\u6570\u9650\u5236\u3002\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<ul>\n<li><strong>\u8bf7\u6c42\u901f\u7387\u9650\u5236<\/strong>\uff1a\u4f7f\u7528<code>time.sleep()<\/code>\u6765\u63a7\u5236\u8bf7\u6c42\u7684\u9891\u7387\u3002<\/li>\n<li><strong>\u9519\u8bef\u5904\u7406<\/strong>\uff1a\u5904\u7406\u53ef\u80fd\u7684\u9519\u8bef\uff0c\u5982\u8bf7\u6c42\u5931\u8d25\u3001\u8d85\u65f6\u7b49\u3002<\/li>\n<\/ul>\n<p><pre><code class=\"language-python\">import time<\/p>\n<p>def get_phone_number_with_retry(name, retries=3):<\/p>\n<p>    api_key = &quot;your_api_key&quot;<\/p>\n<p>    url = f&quot;https:\/\/api.example.com\/phone_lookup?name={name}&amp;api_key={api_key}&quot;<\/p>\n<p>    for _ in range(retries):<\/p>\n<p>        response = requests.get(url)<\/p>\n<p>        if response.status_code == 200:<\/p>\n<p>            data = response.json()<\/p>\n<p>            phone_number = data[&#39;phone_number&#39;]<\/p>\n<p>            return phone_number<\/p>\n<p>        else:<\/p>\n<p>            time.sleep(1)  # \u7b49\u5f851\u79d2\u540e\u91cd\u8bd5<\/p>\n<p>    return None<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u672c\u5730\u6570\u636e\u5e93\u67e5\u8be2<\/h3>\n<\/p>\n<p><p>\u5982\u679c\u4f60\u6709\u4e00\u4e2a\u5305\u542b\u4eba\u540d\u548c\u7535\u8bdd\u53f7\u7801\u7684\u672c\u5730\u6570\u636e\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528SQL\u67e5\u8be2\u6765\u83b7\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528SQLite\u6570\u636e\u5e93<\/h4>\n<\/p>\n<p><p>SQLite\u662f\u4e00\u4e2a\u8f7b\u91cf\u7ea7\u7684\u5173\u7cfb\u578b\u6570\u636e\u5e93\uff0c\u9002\u7528\u4e8e\u5c0f\u578b\u9879\u76ee\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528SQLite\u67e5\u8be2\u7535\u8bdd\u53f7\u7801\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import sqlite3<\/p>\n<p>def get_phone_number(name):<\/p>\n<p>    conn = sqlite3.connect(&#39;contacts.db&#39;)<\/p>\n<p>    cursor = conn.cursor()<\/p>\n<p>    cursor.execute(&quot;SELECT phone_number FROM contacts WHERE name=?&quot;, (name,))<\/p>\n<p>    result = cursor.fetchone()<\/p>\n<p>    conn.close()<\/p>\n<p>    if result:<\/p>\n<p>        return result[0]<\/p>\n<p>    else:<\/p>\n<p>        return None<\/p>\n<p>name = &quot;John Doe&quot;<\/p>\n<p>print(get_phone_number(name))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u8fde\u63a5\u5230SQLite\u6570\u636e\u5e93\uff0c\u6267\u884c\u67e5\u8be2\uff0c\u5e76\u8fd4\u56de\u7535\u8bdd\u53f7\u7801\u3002<\/p>\n<\/p>\n<p><h4>2. \u4f7f\u7528Pandas\u8bfb\u53d6CSV\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u5982\u679c\u7535\u8bdd\u53f7\u7801\u5b58\u50a8\u5728CSV\u6587\u4ef6\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528Pandas\u5e93\u6765\u8bfb\u53d6\u548c\u67e5\u8be2\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<p>def get_phone_number(name):<\/p>\n<p>    df = pd.read_csv(&#39;contacts.csv&#39;)<\/p>\n<p>    result = df[df[&#39;name&#39;] == name]<\/p>\n<p>    if not result.empty:<\/p>\n<p>        return result.iloc[0][&#39;phone_number&#39;]<\/p>\n<p>    else:<\/p>\n<p>        return None<\/p>\n<p>name = &quot;John Doe&quot;<\/p>\n<p>print(get_phone_number(name))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528Pandas\u8bfb\u53d6CSV\u6587\u4ef6\uff0c\u5e76\u6839\u636e\u4eba\u540d\u67e5\u8be2\u7535\u8bdd\u53f7\u7801\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528Python\u901a\u8fc7\u4eba\u540d\u67e5\u627e\u7535\u8bdd\u53f7\u7801\u7684\u65b9\u6cd5\u6709\u5f88\u591a\uff0c\u5177\u4f53\u9009\u62e9\u54ea\u79cd\u65b9\u6cd5\u53d6\u51b3\u4e8e\u6570\u636e\u7684\u6765\u6e90\u548c\u5177\u4f53\u9700\u6c42\u3002<strong>Web Scraping\u9002\u7528\u4e8e\u4ece\u7f51\u7ad9\u63d0\u53d6\u516c\u5f00\u6570\u636e\uff0cAPI\u8c03\u7528\u9002\u7528\u4e8e\u4f7f\u7528\u7b2c\u4e09\u65b9\u670d\u52a1\uff0c\u672c\u5730\u6570\u636e\u5e93\u67e5\u8be2\u9002\u7528\u4e8e\u7ba1\u7406\u81ea\u5df1\u7684\u6570\u636e<\/strong>\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u80fd\u9700\u8981\u7ed3\u5408\u591a\u79cd\u65b9\u6cd5\u6765\u5b9e\u73b0\u6700\u4f73\u6548\u679c\u3002\u5e0c\u671b\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u80fd\u591f\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u7406\u89e3\u5982\u4f55\u4f7f\u7528Python\u901a\u8fc7\u4eba\u540d\u67e5\u627e\u7535\u8bdd\u53f7\u7801\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u4ece\u4eba\u540d\u83b7\u53d6\u7535\u8bdd\u53f7\u7801\u7684\u6700\u4f73\u65b9\u6cd5\u662f\u4ec0\u4e48\uff1f<\/strong><br \/>\u83b7\u53d6\u7535\u8bdd\u53f7\u7801\u7684\u65b9\u5f0f\u6709\u5f88\u591a\uff0c\u4f7f\u7528Python\u53ef\u4ee5\u901a\u8fc7\u4e0d\u540c\u7684API\u6216\u5e93\u6765\u5b9e\u73b0\u3002\u5e38\u89c1\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u4ece\u516c\u5f00\u7684\u793e\u4ea4\u5a92\u4f53\u6216\u6570\u636e\u5e93\u4e2d\u63d0\u53d6\u6570\u636e\uff0c\u6216\u8005\u4f7f\u7528\u7b2c\u4e09\u65b9API\uff08\u5982Twilio\u6216Numverify\uff09\u6765\u67e5\u8be2\u7535\u8bdd\u53f7\u7801\u3002\u786e\u4fdd\u9075\u5faa\u9690\u79c1\u653f\u7b56\u548c\u6cd5\u5f8b\u89c4\u5b9a\uff0c\u4ee5\u5408\u6cd5\u65b9\u5f0f\u83b7\u53d6\u6570\u636e\u3002<\/p>\n<p><strong>\u5728Python\u4e2d\u5982\u4f55\u5904\u7406\u4eba\u540d\u548c\u7535\u8bdd\u53f7\u7801\u7684\u6570\u636e\u683c\u5f0f\uff1f<\/strong><br \/>\u5904\u7406\u4eba\u540d\u548c\u7535\u8bdd\u53f7\u7801\u65f6\uff0c\u901a\u5e38\u9700\u8981\u5c06\u6570\u636e\u5b58\u50a8\u5728\u5408\u9002\u7684\u6570\u636e\u7ed3\u6784\u4e2d\uff0c\u4f8b\u5982\u5b57\u5178\u6216\u6570\u636e\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528Pandas\u5e93\u6765\u5904\u7406\u548c\u5206\u6790\u8fd9\u4e9b\u6570\u636e\uff0c\u786e\u4fdd\u6e05\u6d17\u548c\u6807\u51c6\u5316\u4eba\u540d\u548c\u7535\u8bdd\u53f7\u7801\u683c\u5f0f\uff0c\u4ee5\u63d0\u9ad8\u67e5\u8be2\u7684\u51c6\u786e\u6027\u548c\u6548\u7387\u3002<\/p>\n<p><strong>\u4f7f\u7528Python\u67e5\u627e\u7535\u8bdd\u53f7\u7801\u65f6\u5e94\u6ce8\u610f\u54ea\u4e9b\u9690\u79c1\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u67e5\u627e\u7535\u8bdd\u53f7\u7801\u65f6\uff0c\u5fc5\u987b\u5c0a\u91cd\u7528\u6237\u7684\u9690\u79c1\u6743\u3002\u83b7\u53d6\u548c\u4f7f\u7528\u4e2a\u4eba\u4fe1\u606f\u5e94\u9075\u5faa\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\uff0c\u5982GDPR\u6216CCPA\u3002\u6b64\u5916\uff0c\u786e\u4fdd\u5728\u8fdb\u884c\u6570\u636e\u5904\u7406\u65f6\u91c7\u53d6\u9002\u5f53\u7684\u5b89\u5168\u63aa\u65bd\uff0c\u9632\u6b62\u6570\u636e\u6cc4\u9732\u6216\u6ee5\u7528\u3002\u4f7f\u7528API\u65f6\uff0c\u9009\u62e9\u4fe1\u8a89\u826f\u597d\u7684\u670d\u52a1\u63d0\u4f9b\u5546\u4e5f\u81f3\u5173\u91cd\u8981\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5982\u4f55\u7528Python\u901a\u8fc7\u4eba\u540d\u67e5\u53f7\u7801 \u8981\u4f7f\u7528Python\u901a\u8fc7\u4eba\u540d\u67e5\u627e\u7535\u8bdd\u53f7\u7801\uff0c\u53ef\u4ee5\u4f7f\u7528Web Scraping\u3001A [&hellip;]","protected":false},"author":3,"featured_media":1059573,"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\/1059558"}],"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=1059558"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1059558\/revisions"}],"predecessor-version":[{"id":1059575,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1059558\/revisions\/1059575"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1059573"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1059558"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1059558"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1059558"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}