{"id":1017117,"date":"2024-12-27T12:22:45","date_gmt":"2024-12-27T04:22:45","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1017117.html"},"modified":"2024-12-27T12:22:47","modified_gmt":"2024-12-27T04:22:47","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e7%96%ab%e8%8b%97%e6%8e%a5%e7%a7%8d","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1017117.html","title":{"rendered":"python\u5982\u4f55\u722c\u75ab\u82d7\u63a5\u79cd"},"content":{"rendered":"

\"python\u5982\u4f55\u722c\u75ab\u82d7\u63a5\u79cd\"<\/p>\n

\u5728Python\u4e2d\uff0c\u722c\u53d6\u75ab\u82d7\u63a5\u79cd\u6570\u636e\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u6280\u672f\u3001\u8c03\u7528\u516c\u5f00API\u3001\u89e3\u6790HTML\u9875\u9762<\/strong>\u7b49\u65b9\u6cd5\u5b9e\u73b0\u3002\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u6280\u672f<\/strong>\u662f\u5176\u4e2d\u4e00\u79cd\u5e38\u89c1\u7684\u65b9\u6cd5\uff0c\u901a\u8fc7\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\u4ece\u7279\u5b9a\u7f51\u7ad9\u83b7\u53d6\u6570\u636e\u3002\u8fd9\u9700\u8981\u4e86\u89e3\u76ee\u6807\u7f51\u7ad9\u7684\u7ed3\u6784\u548c\u6570\u636e\u6240\u5728\u7684\u4f4d\u7f6e\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u8ba8\u8bba\u5982\u4f55\u901a\u8fc7Python\u5b9e\u73b0\u8fd9\u4e9b\u65b9\u6cd5\u4e2d\u7684\u4e00\u79cd\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u6280\u672f<\/h3>\n<\/p>\n

\u7f51\u7edc\u722c\u866b\u662f\u4e00\u79cd\u81ea\u52a8\u8bbf\u95ee\u4e92\u8054\u7f51\u5e76\u4ece\u4e2d\u63d0\u53d6\u4fe1\u606f\u7684\u7a0b\u5e8f\u3002\u4f7f\u7528Python\u7f16\u5199\u7f51\u7edc\u722c\u866b\u53ef\u4ee5\u975e\u5e38\u9ad8\u6548\u5730\u6293\u53d6\u548c\u5206\u6790\u5728\u7ebf\u6570\u636e\u3002<\/p>\n<\/p>\n

1. \u5b89\u88c5\u5fc5\u8981\u7684Python\u5e93<\/h4>\n<\/p>\n

\u5728\u5f00\u59cb\u7f16\u5199\u7f51\u7edc\u722c\u866b\u4e4b\u524d\uff0c\u9700\u8981\u5b89\u88c5\u4e00\u4e9b\u5fc5\u8981\u7684Python\u5e93\uff0c\u5982requests<\/code>\u548cBeautifulSoup<\/code>\u3002requests<\/code>\u5e93\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u800cBeautifulSoup<\/code>\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\u3002<\/p>\n<\/p>\n

pip install requests beautifulsoup4<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u53d1\u9001HTTP\u8bf7\u6c42<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u9700\u8981\u786e\u5b9a\u76ee\u6807\u7f51\u7ad9\u7684URL\uff0c\u7136\u540e\u4f7f\u7528requests<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u4ee5\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
url = "https:\/\/example.com\/vaccine-data"<\/p>\n
response = requests.get(url)<\/p>\n
html_content = response.text<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u91cc\uff0cresponse.text<\/code>\u5305\u542b\u4e86\u7f51\u9875\u7684HTML\u4ee3\u7801\u3002<\/p>\n<\/p>\n
3. \u89e3\u6790HTML\u6587\u6863<\/h4>\n<\/p>\n
\u4f7f\u7528BeautifulSoup<\/code>\u89e3\u6790HTML\u6587\u6863\uff0c\u4ece\u4e2d\u63d0\u53d6\u9700\u8981\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n
data_table = soup.find('table', {'id': 'vaccine-data'})<\/p>\n
rows = data_table.find_all('tr')<\/p>\n
for row in rows:<\/p>\n
    cols = row.find_all('td')<\/p>\n
    data = [col.text for col in cols]<\/p>\n
    print(data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u5047\u8bbe\u75ab\u82d7\u6570\u636e\u88ab\u5b58\u50a8\u5728\u4e00\u4e2aHTML\u8868\u683c\u4e2d\uff0c\u901a\u8fc7\u67e5\u627e\u8868\u683c\u7684id<\/code>\u5c5e\u6027\u6765\u5b9a\u4f4d\u5b83\uff0c\u5e76\u63d0\u53d6\u51fa\u6bcf\u4e00\u884c\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u8c03\u7528\u516c\u5f00API<\/h3>\n<\/p>\n
\u8bb8\u591a\u56fd\u5bb6\u548c\u7ec4\u7ec7\u63d0\u4f9b\u516c\u5171API\u6765\u63d0\u4f9b\u6700\u65b0\u7684\u75ab\u82d7\u63a5\u79cd\u6570\u636e\u3002\u8fd9\u4e9bAPI\u901a\u5e38\u66f4\u52a0\u53ef\u9760\u548c\u6613\u4e8e\u4f7f\u7528\uff0c\u56e0\u4e3a\u5b83\u4eec\u63d0\u4f9b\u4e86\u7ed3\u6784\u5316\u7684\u6570\u636e\u683c\u5f0f\uff0c\u5982JSON\u3002<\/p>\n<\/p>\n
1. \u67e5\u627e\u5408\u9002\u7684API<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u67e5\u627e\u4e00\u4e2a\u63d0\u4f9b\u75ab\u82d7\u63a5\u79cd\u6570\u636e\u7684\u516c\u5171API\u3002\u4f8b\u5982\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528\u7531\u653f\u5e9c\u6216\u536b\u751f\u7ec4\u7ec7\u63d0\u4f9b\u7684API\u3002<\/p>\n<\/p>\n
2. \u53d1\u9001API\u8bf7\u6c42<\/h4>\n<\/p>\n
\u4f7f\u7528requests<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u5230API\u7684\u7aef\u70b9\uff0c\u5e76\u89e3\u6790\u8fd4\u56de\u7684JSON\u6570\u636e\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
api_url = "https:\/\/api.example.com\/vaccine-data"<\/p>\n
response = requests.get(api_url)<\/p>\n
data = response.json()<\/p>\n
for record in data['records']:<\/p>\n
    print(record['date'], record['location'], record['vaccinated'])<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u5047\u8bbeAPI\u8fd4\u56de\u7684\u6570\u636e\u662fJSON\u683c\u5f0f\uff0c\u5e76\u5305\u542b\u4e00\u4e2a\u540d\u4e3arecords<\/code>\u7684\u6570\u7ec4\uff0c\u5176\u4e2d\u6bcf\u4e2a\u8bb0\u5f55\u5305\u542b\u65e5\u671f\u3001\u5730\u70b9\u548c\u63a5\u79cd\u4eba\u6570\u7684\u4fe1\u606f\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u89e3\u6790HTML\u9875\u9762<\/h3>\n<\/p>\n
\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u6570\u636e\u53ef\u80fd\u5d4c\u5165\u5728HTML\u9875\u9762\u7684\u5176\u4ed6\u90e8\u5206\uff0c\u4f8b\u5982JavaScript\u4ee3\u7801\u6216\u5d4c\u5165\u5f0f\u8868\u683c\u4e2d\u3002<\/p>\n<\/p>\n
1. \u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u6570\u636e<\/h4>\n<\/p>\n
\u5982\u679c\u6570\u636e\u5d4c\u5165\u5728JavaScript\u4ee3\u7801\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u3002<\/p>\n<\/p>\n
import re<\/p>\n
pattern = re.compile(r"var vaccineData = (\\[.*?\\]);")<\/p>\n
match = pattern.search(html_content)<\/p>\n
if match:<\/p>\n
    data = match.group(1)<\/p>\n
    print(data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u91cc\uff0c\u5047\u8bbe\u6570\u636e\u88ab\u5b9a\u4e49\u4e3aJavaScript\u53d8\u91cfvaccineData<\/code>\u3002\u6b63\u5219\u8868\u8fbe\u5f0f\u7528\u4e8e\u5339\u914d\u5e76\u63d0\u53d6\u8fd9\u4e2a\u53d8\u91cf\u7684\u503c\u3002<\/p>\n<\/p>\n
2. \u5904\u7406\u52a8\u6001\u5185\u5bb9<\/h4>\n<\/p>\n
\u5982\u679c\u6570\u636e\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u53ef\u80fd\u9700\u8981\u4f7f\u7528\u7c7b\u4f3cSelenium<\/code>\u7684\u5de5\u5177\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u5e76\u6267\u884cJavaScript\u3002<\/p>\n<\/p>\n
from selenium import webdriver<\/p>\n
driver = webdriver.Chrome()<\/p>\n
driver.get("https:\/\/example.com\/vaccine-data")<\/p>\n
\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5e76\u6267\u884cJavaScript<\/strong><\/h2>\n
driver.implicitly_wAI<\/a>t(10)<\/p>\n
data_element = driver.find_element_by_id('vaccine-data')<\/p>\n
print(data_element.text)<\/p>\n
driver.quit()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u6570\u636e\u5b58\u50a8\u548c\u5904\u7406<\/h3>\n<\/p>\n
\u5728\u6210\u529f\u83b7\u53d6\u6570\u636e\u540e\uff0c\u4e0b\u4e00\u6b65\u662f\u5b58\u50a8\u548c\u5904\u7406\u8fd9\u4e9b\u6570\u636e\uff0c\u4ee5\u4fbf\u8fdb\u884c\u5206\u6790\u6216\u5c55\u793a\u3002<\/p>\n<\/p>\n
1. \u5b58\u50a8\u6570\u636e<\/h4>\n<\/p>\n
\u53ef\u4ee5\u5c06\u6570\u636e\u5b58\u50a8\u5728CSV\u6587\u4ef6\u3001\u6570\u636e\u5e93\u6216\u5176\u4ed6\u5408\u9002\u7684\u683c\u5f0f\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u4f7f\u7528\u3002<\/p>\n<\/p>\n
import csv<\/p>\n
with open('vaccine_data.csv', mode='w', newline='') as file:<\/p>\n
    writer = csv.writer(file)<\/p>\n
    writer.writerow(['Date', 'Location', 'Vaccinated'])<\/p>\n
    for record in data['records']:<\/p>\n
        writer.writerow([record['date'], record['location'], record['vaccinated']])<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u6570\u636e\u5206\u6790<\/h4>\n<\/p>\n
\u4f7f\u7528Python\u7684pandas<\/code>\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u6790\u548c\u53ef\u89c6\u5316\u3002<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
df = pd.read_csv('vaccine_data.csv')<\/p>\n
print(df.describe())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u6ce8\u610f\u4e8b\u9879<\/h3>\n<\/p>\n
1. \u9075\u5b88\u6cd5\u5f8b\u6cd5\u89c4<\/h4>\n<\/p>\n
\u5728\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u65f6\uff0c\u9700\u8981\u786e\u4fdd\u9075\u5b88\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u7684robots.txt<\/code>\u534f\u8bae\uff0c\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u8d1f\u62c5\u3002<\/p>\n<\/p>\n
2. \u6570\u636e\u51c6\u786e\u6027\u548c\u53ca\u65f6\u6027<\/h4>\n<\/p>\n
\u786e\u4fdd\u83b7\u53d6\u7684\u6570\u636e\u662f\u51c6\u786e\u548c\u53ca\u65f6\u7684\uff0c\u5c24\u5176\u662f\u5728\u5904\u7406\u4e0e\u516c\u5171\u5065\u5eb7\u76f8\u5173\u7684\u654f\u611f\u6570\u636e\u65f6\u3002<\/p>\n<\/p>\n
3. \u8003\u8651\u6570\u636e\u9690\u79c1<\/h4>\n<\/p>\n
\u5728\u5904\u7406\u75ab\u82d7\u63a5\u79cd\u6570\u636e\u65f6\uff0c\u6ce8\u610f\u4e0d\u8981\u8fdd\u53cd\u6570\u636e\u9690\u79c1\u6cd5\u5f8b\uff0c\u5982GDPR\u7b49\u3002<\/p>\n<\/p>\n
\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7Python\u722c\u53d6\u75ab\u82d7\u63a5\u79cd\u6570\u636e\u53ef\u4ee5\u4f7f\u7528\u591a\u79cd\u65b9\u6cd5\uff0c\u5305\u62ec\u7f51\u7edc\u722c\u866b\u548cAPI\u8c03\u7528\u3002\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u53d6\u51b3\u4e8e\u6570\u636e\u7684\u53ef\u7528\u6027\u548c\u7ed3\u6784\u3002\u5728\u5b9e\u65bd\u7f51\u7edc\u722c\u866b\u65f6\uff0c\u9700\u8981\u5173\u6ce8\u6cd5\u5f8b\u5408\u89c4\u6027\u548c\u6570\u636e\u9690\u79c1\u95ee\u9898\u3002\u65e0\u8bba\u9009\u62e9\u54ea\u79cd\u65b9\u6cd5\uff0c\u786e\u4fdd\u6570\u636e\u7684\u51c6\u786e\u6027\u548c\u53ca\u65f6\u6027\u662f\u81f3\u5173\u91cd\u8981\u7684\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u75ab\u82d7\u63a5\u79cd\u6570\u636e\uff1f<\/strong>
\u4f7f\u7528Python\u722c\u53d6\u75ab\u82d7\u63a5\u79cd\u6570\u636e\u7684\u6b65\u9aa4\u4e3b\u8981\u5305\u62ec\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u786e\u5b9a\u76ee\u6807\u7f51\u7ad9\u3001\u5206\u6790\u7f51\u9875\u7ed3\u6784\u3001\u63d0\u53d6\u6570\u636e\u7b49\u3002\u5e38\u7528\u7684\u5e93\u6709Requests\u7528\u4e8e\u53d1\u9001\u7f51\u7edc\u8bf7\u6c42\uff0cBeautifulSoup\u6216lxml\u7528\u4e8e\u89e3\u6790HTML\u4ee3\u7801\uff0cPandas\u7528\u4e8e\u5904\u7406\u548c\u5b58\u50a8\u6570\u636e\u3002\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684\u722c\u866b\u534f\u8bae\uff0c\u907f\u514d\u5bf9\u670d\u52a1\u5668\u9020\u6210\u8d1f\u62c5\u3002<\/p>\n
\u5728\u722c\u53d6\u75ab\u82d7\u63a5\u79cd\u4fe1\u606f\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong>
\u5728\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u65f6\uff0c\u9075\u5faa\u6cd5\u5f8b\u6cd5\u89c4\u662f\u81f3\u5173\u91cd\u8981\u7684\u3002\u786e\u4fdd\u4e86\u89e3\u5e76\u9075\u5b88\u76ee\u6807\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u548crobots.txt\u6587\u4ef6\u4e2d\u7684\u722c\u866b\u89c4\u5219\u3002\u5c0a\u91cd\u7528\u6237\u9690\u79c1\uff0c\u4e0d\u5e94\u6536\u96c6\u654f\u611f\u4fe1\u606f\uff0c\u907f\u514d\u6ee5\u7528\u6570\u636e\u3002\u6b64\u5916\uff0c\u8003\u8651\u6570\u636e\u7684\u4f7f\u7528\u76ee\u7684\uff0c\u786e\u4fdd\u4e0d\u5bf9\u6570\u636e\u8fdb\u884c\u4e0d\u5f53\u5229\u7528\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u722c\u53d6\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong>
\u8bb8\u591a\u7f51\u7ad9\u4f1a\u90e8\u7f72\u53cd\u722c\u866b\u673a\u5236\u6765\u9632\u6b62\u6570\u636e\u88ab\u6293\u53d6\u3002\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3001\u4f7f\u7528\u4ee3\u7406IP\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u540c\u4e00\u9875\u9762\u3001\u4ee5\u53ca\u589e\u52a0\u968f\u673a\u5ef6\u8fdf\u6765\u964d\u4f4e\u88ab\u8bc6\u522b\u7684\u98ce\u9669\u3002\u6b64\u5916\uff0c\u4f7f\u7528selenium\u7b49\u5de5\u5177\u8fdb\u884c\u52a8\u6001\u7f51\u9875\u6293\u53d6\u4e5f\u662f\u4e00\u79cd\u6709\u6548\u7684\u89e3\u51b3\u65b9\u6848\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\uff0c\u722c\u53d6\u75ab\u82d7\u63a5\u79cd\u6570\u636e\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u6280\u672f\u3001\u8c03\u7528\u516c\u5f00API\u3001\u89e3\u6790HTML\u9875\u9762\u7b49\u65b9\u6cd5\u5b9e\u73b0\u3002\u4f7f\u7528\u7f51 […]","protected":false},"author":3,"featured_media":1017122,"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\/1017117"}],"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=1017117"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1017117\/revisions"}],"predecessor-version":[{"id":1017125,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1017117\/revisions\/1017125"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1017122"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1017117"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1017117"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1017117"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}