{"id":1077002,"date":"2025-01-08T11:58:18","date_gmt":"2025-01-08T03:58:18","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1077002.html"},"modified":"2025-01-08T11:58:20","modified_gmt":"2025-01-08T03:58:20","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e7%88%ac%e6%97%85%e6%b8%b8%e5%ae%a2%e6%88%b7%e4%bf%a1%e6%81%af-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1077002.html","title":{"rendered":"\u5982\u4f55\u7528python\u722c\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f"},"content":{"rendered":"

\"\u5982\u4f55\u7528python\u722c\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f\"<\/p>\n

\u5982\u4f55\u7528python\u722c\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f<\/strong><\/p>\n<\/p>\n

\u5728\u7528Python\u722c\u53d6\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f\u65f6\uff0c\u4e3b\u8981\u7684\u65b9\u6cd5\u6709\u4f7f\u7528requests\u5e93\u3001BeautifulSoup\u89e3\u6790\u7f51\u9875\u3001Scrapy\u6846\u67b6\u3001Selenium\u81ea\u52a8\u5316\u6d4b\u8bd5\u5de5\u5177<\/strong>\u3002\u5176\u4e2d\uff0crequests\u5e93\u548cBeautifulSoup\u89e3\u6790\u7f51\u9875<\/strong>\u662f\u6700\u57fa\u7840\u548c\u5e38\u7528\u7684\u65b9\u5f0f\uff0c\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528\u8fd9\u4e9b\u5de5\u5177\u6765\u5b9e\u73b0\u8fd9\u4e00\u76ee\u6807\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h2>\n<\/p>\n

requests\u5e93\u662fPython\u4e2d\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684HTTP\u5e93\uff0c\u53ef\u4ee5\u7528\u6765\u53d1\u9001\u5404\u79cdHTTP\u8bf7\u6c42\u3002\u4f7f\u7528requests\u5e93\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u662f\u722c\u866b\u7684\u7b2c\u4e00\u6b65\u3002<\/p>\n<\/p>\n

import requests<\/p>\n
url = 'https:\/\/example.com\/tourist-info'<\/p>\n
response = requests.get(url)<\/p>\n
if response.status_code == 200:<\/p>\n
    print("Successfully fetched the webpage!")<\/p>\n
    content = response.text<\/p>\n
else:<\/p>\n
    print("FAI<\/a>led to fetch the webpage. Status code:", response.status_code)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165requests\u5e93\uff0c\u7136\u540e\u4f7f\u7528requests.get()\u65b9\u6cd5\u53d1\u9001\u4e00\u4e2aGET\u8bf7\u6c42\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u68c0\u67e5\u54cd\u5e94\u72b6\u6001\u7801\u662f\u5426\u4e3a200\uff0c\u5982\u679c\u662f\uff0c\u5219\u8868\u793a\u8bf7\u6c42\u6210\u529f\uff0c\u53ef\u4ee5\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/h2>\n<\/p>\n
\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u4e0b\u4e00\u6b65\u662f\u89e3\u6790\u8fd9\u4e9b\u5185\u5bb9\u5e76\u63d0\u53d6\u6211\u4eec\u9700\u8981\u7684\u4fe1\u606f\u3002BeautifulSoup\u662f\u4e00\u4e2a\u975e\u5e38\u6d41\u884c\u7684Python\u5e93\uff0c\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
soup = BeautifulSoup(content, 'html.parser')<\/p>\n
Example: Extracting all tourist names<\/strong><\/h2>\n
tourist_names = []<\/p>\n
for name_tag in soup.find_all('h2', class_='tourist-name'):<\/p>\n
    tourist_names.append(name_tag.text)<\/p>\n
print("Tourist Names:", tourist_names)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u5bfc\u5165BeautifulSoup\u5e93\uff0c\u5e76\u5c06\u7f51\u9875\u5185\u5bb9\u4f20\u9012\u7ed9BeautifulSoup\u5bf9\u8c61\u8fdb\u884c\u89e3\u6790\u3002\u7136\u540e\u4f7f\u7528find_all()\u65b9\u6cd5\u67e5\u627e\u5305\u542b\u5ba2\u6237\u4fe1\u606f\u7684HTML\u6807\u7b7e\uff0c\u5e76\u63d0\u53d6\u5176\u4e2d\u7684\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u722c\u53d6<\/h2>\n<\/p>\n
Scrapy\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u7528\u4e8e\u5927\u89c4\u6a21\u6570\u636e\u722c\u53d6\u548c\u5904\u7406\u3002\u5b83\u63d0\u4f9b\u4e86\u66f4\u591a\u7684\u529f\u80fd\u548c\u66f4\u597d\u7684\u6027\u80fd\uff0c\u9002\u5408\u5904\u7406\u590d\u6742\u7684\u7f51\u7ad9\u548c\u5927\u91cf\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
\u5b89\u88c5Scrapy<\/h3>\n<\/p>\n
\u9996\u5148\uff0c\u5b89\u88c5Scrapy\uff1a<\/p>\n<\/p>\n
pip install scrapy<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u521b\u5efa\u4e00\u4e2aScrapy\u9879\u76ee<\/h3>\n<\/p>\n
\u4f7f\u7528Scrapy\u547d\u4ee4\u884c\u5de5\u5177\u521b\u5efa\u4e00\u4e2a\u65b0\u9879\u76ee\uff1a<\/p>\n<\/p>\n
scrapy startproject tourist_info<\/p>\n
cd tourist_info<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u521b\u5efa\u4e00\u4e2aSpider<\/h3>\n<\/p>\n
\u5728Scrapy\u9879\u76ee\u4e2d\u521b\u5efa\u4e00\u4e2aSpider\uff0c\u7528\u4e8e\u5b9a\u4e49\u722c\u53d6\u903b\u8f91\uff1a<\/p>\n<\/p>\n
scrapy genspider tourist_spider example.com<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u7f16\u5199Spider<\/h3>\n<\/p>\n
\u7f16\u8f91\u751f\u6210\u7684spider\u6587\u4ef6tourist_spider.py<\/code>\uff0c\u7f16\u5199\u722c\u53d6\u903b\u8f91\uff1a<\/p>\n<\/p>\n
import scrapy<\/p>\n
class TouristSpider(scrapy.Spider):<\/p>\n
    name = 'tourist_spider'<\/p>\n
    start_urls = ['https:\/\/example.com\/tourist-info']<\/p>\n
    def parse(self, response):<\/p>\n
        for tourist in response.css('div.tourist'):<\/p>\n
            yield {<\/p>\n
                'name': tourist.css('h2.tourist-name::text').get(),<\/p>\n
                'age': tourist.css('span.tourist-age::text').get(),<\/p>\n
                'location': tourist.css('span.tourist-location::text').get(),<\/p>\n
            }<\/p>\n
        next_page = response.css('a.next-page::attr(href)').get()<\/p>\n
        if next_page is not None:<\/p>\n
            yield response.follow(next_page, self.parse)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd0\u884cSpider<\/h3>\n<\/p>\n
\u4f7f\u7528Scrapy\u547d\u4ee4\u884c\u5de5\u5177\u8fd0\u884cSpider\uff1a<\/p>\n<\/p>\n
scrapy crawl tourist_spider -o tourists.json<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd0\u884c\u4ee5\u4e0a\u547d\u4ee4\u540e\uff0cScrapy\u5c06\u5f00\u59cb\u722c\u53d6\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f\uff0c\u5e76\u5c06\u7ed3\u679c\u4fdd\u5b58\u5230tourists.json<\/code>\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n
\u56db\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u52a8\u6001\u7f51\u9875\u722c\u53d6<\/h2>\n<\/p>\n
\u5bf9\u4e8e\u4e00\u4e9b\u9700\u8981JavaScript\u6e32\u67d3\u7684\u7f51\u9875\uff0crequests\u548cBeautifulSoup\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u5230\u5b8c\u6574\u7684\u7f51\u9875\u5185\u5bb9\u3002\u8fd9\u65f6\u5019\u53ef\u4ee5\u4f7f\u7528Selenium\uff0cSelenium\u662f\u4e00\u4e2a\u81ea\u52a8\u5316\u6d4b\u8bd5\u5de5\u5177\uff0c\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u64cd\u4f5c\u6d4f\u89c8\u5668\u3002<\/p>\n<\/p>\n
\u5b89\u88c5Selenium<\/h3>\n<\/p>\n
\u9996\u5148\uff0c\u5b89\u88c5Selenium\uff1a<\/p>\n<\/p>\n
pip install selenium<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u914d\u7f6e\u6d4f\u89c8\u5668\u9a71\u52a8<\/h3>\n<\/p>\n
\u4e0b\u8f7d\u5bf9\u5e94\u6d4f\u89c8\u5668\u7684\u9a71\u52a8\u7a0b\u5e8f\uff08\u5982ChromeDriver\uff09\u5e76\u5c06\u5176\u6dfb\u52a0\u5230\u7cfb\u7edf\u8def\u5f84\u4e2d\u3002<\/p>\n<\/p>\n
\u7f16\u5199\u722c\u866b\u4ee3\u7801<\/h3>\n<\/p>\n
\u4f7f\u7528Selenium\u7f16\u5199\u722c\u866b\u4ee3\u7801\uff0c\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff1a<\/p>\n<\/p>\n
from selenium import webdriver<\/p>\n
from selenium.webdriver.common.by import By<\/p>\n
from selenium.webdriver.common.keys import Keys<\/p>\n
driver = webdriver.Chrome()<\/p>\n
url = 'https:\/\/example.com\/tourist-info'<\/p>\n
driver.get(url)<\/p>\n
Example: Extracting tourist names<\/strong><\/h2>\n
tourist_names = []<\/p>\n
name_elements = driver.find_elements(By.CLASS_NAME, 'tourist-name')<\/p>\n
for element in name_elements:<\/p>\n
    tourist_names.append(element.text)<\/p>\n
print("Tourist Names:", tourist_names)<\/p>\n
driver.quit()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u521b\u5efa\u4e00\u4e2a\u6d4f\u89c8\u5668\u5b9e\u4f8b\uff0c\u5e76\u4f7f\u7528get()\u65b9\u6cd5\u6253\u5f00\u76ee\u6807\u7f51\u9875\u3002\u7136\u540e\u4f7f\u7528find_elements()\u65b9\u6cd5\u67e5\u627e\u5305\u542b\u5ba2\u6237\u4fe1\u606f\u7684HTML\u5143\u7d20\uff0c\u5e76\u63d0\u53d6\u5176\u4e2d\u7684\u6587\u672c\u5185\u5bb9\u3002\u6700\u540e\uff0c\u5173\u95ed\u6d4f\u89c8\u5668\u5b9e\u4f8b\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u603b\u7ed3<\/h2>\n<\/p>\n
\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u4ecb\u7ecd\u4e86\u51e0\u79cd\u4f7f\u7528Python\u722c\u53d6\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f\u7684\u65b9\u6cd5\uff0c\u5305\u62ecrequests\u5e93\u3001BeautifulSoup\u89e3\u6790\u7f51\u9875\u3001Scrapy\u6846\u67b6\u548cSelenium\u81ea\u52a8\u5316\u6d4b\u8bd5\u5de5\u5177\u3002\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u4f18\u70b9\u548c\u9002\u7528\u573a\u666f\uff0c\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u53ef\u4ee5\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u548c\u6570\u636e\u8d28\u91cf\u3002<\/p>\n<\/p>\n
requests\u5e93\u548cBeautifulSoup\u89e3\u6790\u7f51\u9875<\/strong>\u9002\u5408\u5904\u7406\u9759\u6001\u7f51\u9875\u548c\u5c0f\u89c4\u6a21\u7684\u6570\u636e\u722c\u53d6\uff0cScrapy\u6846\u67b6<\/strong>\u9002\u5408\u5927\u89c4\u6a21\u6570\u636e\u722c\u53d6\u548c\u590d\u6742\u7684\u7f51\u7ad9\u7ed3\u6784\uff0cSelenium<\/strong>\u9002\u5408\u5904\u7406\u9700\u8981JavaScript\u6e32\u67d3\u7684\u52a8\u6001\u7f51\u9875\u3002\u5e0c\u671b\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u80fd\u5e2e\u52a9\u5927\u5bb6\u66f4\u597d\u5730\u638c\u63e1Python\u722c\u866b\u6280\u672f\uff0c\u5e94\u7528\u5230\u5b9e\u9645\u9879\u76ee\u4e2d\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5728\u4f7f\u7528Python\u722c\u53d6\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f\u65f6\uff0c\u5e94\u8be5\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u4f26\u7406\u95ee\u9898\uff1f<\/strong>
\u5728\u8fdb\u884c\u7f51\u9875\u722c\u866b\u65f6\uff0c\u91cd\u8981\u7684\u662f\u9075\u5faa\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u548c\u6761\u4ef6\uff0c\u786e\u4fdd\u5408\u6cd5\u5408\u89c4\u3002\u8bb8\u591a\u7f51\u7ad9\u4f1a\u5728\u5176robots.txt\u6587\u4ef6\u4e2d\u660e\u786e\u8bf4\u660e\u5141\u8bb8\u548c\u7981\u6b62\u7684\u722c\u53d6\u884c\u4e3a\u3002\u5c0a\u91cd\u8fd9\u4e9b\u89c4\u5b9a\u4e0d\u4ec5\u662f\u6cd5\u5f8b\u8981\u6c42\uff0c\u4e5f\u662f\u826f\u597d\u7684\u7f51\u7edc\u9053\u5fb7\u3002\u540c\u65f6\uff0c\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u5730\u8bf7\u6c42\u7f51\u7ad9\uff0c\u4ee5\u514d\u5bf9\u5176\u670d\u52a1\u5668\u9020\u6210\u8d1f\u62c5\u3002<\/p>\n
\u6709\u54ea\u4e9bPython\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u5b9e\u73b0\u722c\u866b\u529f\u80fd\uff1f<\/strong>
Python\u63d0\u4f9b\u4e86\u591a\u4e2a\u5f3a\u5927\u7684\u5e93\u6765\u7b80\u5316\u722c\u866b\u7684\u5f00\u53d1\u8fc7\u7a0b\u3002\u5e38\u7528\u7684\u5e93\u5305\u62ecRequests\uff0c\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff1bBeautifulSoup\uff0c\u65b9\u4fbf\u89e3\u6790\u548c\u63d0\u53d6HTML\u548cXML\u6587\u6863\uff1bScrapy\uff0c\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u8fdb\u884c\u5927\u89c4\u6a21\u7684\u6570\u636e\u6293\u53d6\u3002\u6b64\u5916\uff0cPandas\u53ef\u4ee5\u7528\u4e8e\u6570\u636e\u5904\u7406\u548c\u5b58\u50a8\uff0c\u5e2e\u52a9\u7528\u6237\u66f4\u597d\u5730\u7ba1\u7406\u722c\u53d6\u5230\u7684\u4fe1\u606f\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong>
\u8bb8\u591a\u7f51\u7ad9\u4f7f\u7528\u53cd\u722c\u866b\u6280\u672f\u6765\u4fdd\u62a4\u5176\u6570\u636e\uff0c\u8fd9\u53ef\u80fd\u5305\u62ecIP\u5c01\u7981\u3001\u7528\u6237\u4ee3\u7406\u68c0\u6d4b\u7b49\u3002\u4e3a\u4e86\u5e94\u5bf9\u8fd9\u4e9b\u6311\u6218\uff0c\u53ef\u4ee5\u91c7\u53d6\u4e00\u4e9b\u7b56\u7565\uff0c\u4f8b\u5982\u4f7f\u7528\u4ee3\u7406\u670d\u52a1\u5668\u6765\u66f4\u6362IP\u5730\u5740\uff0c\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u4ee5\u4f2a\u88c5\u8bf7\u6c42\uff0c\u6216\u8005\u8bbe\u7f6e\u968f\u673a\u7684\u7528\u6237\u4ee3\u7406\u5b57\u7b26\u4e32\u3002\u6b64\u5916\uff0c\u9002\u5f53\u7684\u8bf7\u6c42\u95f4\u9694\u548c\u9075\u5faa\u7f51\u7ad9\u7684\u8bbf\u95ee\u9891\u7387\u9650\u5236\u4e5f\u53ef\u4ee5\u964d\u4f4e\u88ab\u68c0\u6d4b\u7684\u98ce\u9669\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5982\u4f55\u7528python\u722c\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f \u5728\u7528Python\u722c\u53d6\u65c5\u6e38\u5ba2\u6237\u4fe1\u606f\u65f6\uff0c\u4e3b\u8981\u7684\u65b9\u6cd5\u6709\u4f7f\u7528requests\u5e93\u3001Be […]","protected":false},"author":3,"featured_media":1077007,"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\/1077002"}],"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=1077002"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1077002\/revisions"}],"predecessor-version":[{"id":1077008,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1077002\/revisions\/1077008"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1077007"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1077002"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1077002"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1077002"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}