{"id":1026594,"date":"2024-12-31T10:43:56","date_gmt":"2024-12-31T02:43:56","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1026594.html"},"modified":"2024-12-31T10:43:59","modified_gmt":"2024-12-31T02:43:59","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e5%9c%a8%e8%b0%b7%e6%ad%8c%e4%b8%8a%e7%88%ac%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1026594.html","title":{"rendered":"\u5982\u4f55\u7528python\u5728\u8c37\u6b4c\u4e0a\u722c\u6570\u636e"},"content":{"rendered":"

\"\u5982\u4f55\u7528python\u5728\u8c37\u6b4c\u4e0a\u722c\u6570\u636e\"<\/p>\n

\u4f7f\u7528Python\u5728\u8c37\u6b4c\u4e0a\u722c\u6570\u636e\u6709\u51e0\u79cd\u65b9\u6cd5\uff1a\u4f7f\u7528Selenium\u81ea\u52a8\u5316\u6d4f\u89c8\u5668\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528Google Custom Search API\u3001\u901a\u8fc7Scrapy\u6846\u67b6\u8fdb\u884c\u722c\u53d6\u3002<\/strong> \u5176\u4e2d\uff0c\u4f7f\u7528Selenium\u81ea\u52a8\u5316\u6d4f\u89c8\u5668\u662f\u6700\u5e38\u89c1\u7684\u65b9\u6cd5\uff0c\u56e0\u4e3a\u5b83\u80fd\u591f\u6a21\u62df\u7528\u6237\u884c\u4e3a\uff0c\u7ed5\u8fc7\u4e00\u4e9b\u53cd\u722c\u866b\u673a\u5236\u3002\u4f8b\u5982\uff0cSelenium\u53ef\u4ee5\u6253\u5f00\u6d4f\u89c8\u5668\uff0c\u8f93\u5165\u5173\u952e\u8bcd\uff0c\u7ffb\u9875\uff0c\u5e76\u6293\u53d6\u641c\u7d22\u7ed3\u679c\u3002\u63a5\u4e0b\u6765\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Selenium\u6765\u5728\u8c37\u6b4c\u4e0a\u722c\u6570\u636e\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u5b89\u88c5\u548c\u914d\u7f6e\u73af\u5883<\/h3>\n<\/p>\n

\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5Selenium\u548cWebDriver\u3002Selenium\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u5b83\u53ef\u4ee5\u63a7\u5236\u6d4f\u89c8\u5668\u8fdb\u884c\u5404\u79cd\u64cd\u4f5c\uff0c\u800cWebDriver\u662fSelenium\u7528\u6765\u4e0e\u6d4f\u89c8\u5668\u8fdb\u884c\u4ea4\u4e92\u7684\u9a71\u52a8\u7a0b\u5e8f\u3002\u4e3a\u4e86\u4f7f\u7528Selenium\uff0c\u6211\u4eec\u8fd8\u9700\u8981\u4e00\u4e2a\u652f\u6301\u7684\u6d4f\u89c8\u5668\uff0c\u4f8b\u5982Google Chrome\uff0c\u4ee5\u53ca\u76f8\u5e94\u7684ChromeDriver\u3002<\/p>\n<\/p>\n

pip install selenium<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u597dSelenium\u540e\uff0c\u6211\u4eec\u9700\u8981\u4e0b\u8f7d\u9002\u5408\u81ea\u5df1Chrome\u7248\u672c\u7684ChromeDriver\uff0c\u5e76\u5c06\u5176\u8def\u5f84\u914d\u7f6e\u5230\u7cfb\u7edf\u73af\u5883\u53d8\u91cf\u4e2d\u3002\u4f60\u53ef\u4ee5\u4eceChromeDriver\u5b98\u65b9\u7f51\u7ad9<\/a>\u4e0b\u8f7d\u9002\u5408\u4f60\u7248\u672c\u7684ChromeDriver\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Selenium\u6253\u5f00\u8c37\u6b4c\u5e76\u641c\u7d22\u5173\u952e\u8bcd<\/h3>\n<\/p>\n
\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5bfc\u5165Selenium\u5e93\uff0c\u5e76\u8bbe\u7f6eChromeDriver\u8def\u5f84\u3002\u7136\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Selenium\u6253\u5f00\u8c37\u6b4c\u4e3b\u9875\uff0c\u5e76\u8f93\u5165\u641c\u7d22\u5173\u952e\u8bcd\u3002<\/p>\n<\/p>\n
from selenium import webdriver<\/p>\n
from selenium.webdriver.common.keys import Keys<\/p>\n
import time<\/p>\n
\u8bbe\u7f6eChromeDriver\u8def\u5f84<\/strong><\/h2>\n
driver_path = '\/path\/to\/chromedriver'<\/p>\n
driver = webdriver.Chrome(driver_path)<\/p>\n
\u6253\u5f00\u8c37\u6b4c\u4e3b\u9875<\/strong><\/h2>\n
driver.get("http:\/\/www.google.com")<\/p>\n
\u627e\u5230\u641c\u7d22\u8f93\u5165\u6846<\/strong><\/h2>\n
search_box = driver.find_element_by_name("q")<\/p>\n
\u8f93\u5165\u641c\u7d22\u5173\u952e\u8bcd\u5e76\u56de\u8f66<\/strong><\/h2>\n
search_box.send_keys("Python web scraping")<\/p>\n
search_box.send_keys(Keys.RETURN)<\/p>\n
\u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/strong><\/h2>\n
time.sleep(3)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u89e3\u6790\u641c\u7d22\u7ed3\u679c<\/h3>\n<\/p>\n
\u5728\u641c\u7d22\u7ed3\u679c\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u9700\u8981\u89e3\u6790\u9875\u9762\u5185\u5bb9\uff0c\u63d0\u53d6\u6211\u4eec\u9700\u8981\u7684\u6570\u636e\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Selenium\u7684find_elements_by_xpath<\/code>\u65b9\u6cd5\u6765\u5b9a\u4f4d\u641c\u7d22\u7ed3\u679c\u3002<\/p>\n<\/p>\n
# \u83b7\u53d6\u6240\u6709\u641c\u7d22\u7ed3\u679c<\/p>\n
results = driver.find_elements_by_xpath('\/\/div[@class="g"]')<\/p>\n
\u904d\u5386\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
for result in results:<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u6807\u9898<\/p>\n
    title = result.find_element_by_xpath('.\/\/h3').text<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u94fe\u63a5<\/p>\n
    link = result.find_element_by_xpath('.\/\/a').get_attribute('href')<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u63cf\u8ff0<\/p>\n
    description = result.find_element_by_xpath('.\/\/span[@class="st"]').text<\/p>\n
    print(f'Title: {title}')<\/p>\n
    print(f'Link: {link}')<\/p>\n
    print(f'Description: {description}')<\/p>\n
    print('-' * 80)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u5904\u7406\u5206\u9875<\/h3>\n<\/p>\n
\u6709\u65f6\u5019\uff0c\u6211\u4eec\u9700\u8981\u83b7\u53d6\u591a\u4e2a\u9875\u9762\u7684\u641c\u7d22\u7ed3\u679c\u3002\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u6211\u4eec\u9700\u8981\u5904\u7406\u5206\u9875\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Selenium\u70b9\u51fb\u201c\u4e0b\u4e00\u9875\u201d\u6309\u94ae\uff0c\u7136\u540e\u91cd\u590d\u4e0a\u8ff0\u6b65\u9aa4\u6293\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n
# \u83b7\u53d6\u4e0b\u4e00\u9875\u6309\u94ae<\/p>\n
next_button = driver.find_element_by_xpath('\/\/a[@id="pnnext"]')<\/p>\n
\u70b9\u51fb\u4e0b\u4e00\u9875\u6309\u94ae<\/strong><\/h2>\n
next_button.click()<\/p>\n
\u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/strong><\/h2>\n
time.sleep(3)<\/p>\n
\u91cd\u65b0\u83b7\u53d6\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
results = driver.find_elements_by_xpath('\/\/div[@class="g"]')<\/p>\n
\u904d\u5386\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
for result in results:<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u6807\u9898<\/p>\n
    title = result.find_element_by_xpath('.\/\/h3').text<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u94fe\u63a5<\/p>\n
    link = result.find_element_by_xpath('.\/\/a').get_attribute('href')<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u63cf\u8ff0<\/p>\n
    description = result.find_element_by_xpath('.\/\/span[@class="st"]').text<\/p>\n
    print(f'Title: {title}')<\/p>\n
    print(f'Link: {link}')<\/p>\n
    print(f'Description: {description}')<\/p>\n
    print('-' * 80)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/h3>\n<\/p>\n
\u6709\u65f6\u5019\uff0c\u5355\u72ec\u4f7f\u7528Selenium\u53ef\u80fd\u4e0d\u591f\u9ad8\u6548\u3002\u6211\u4eec\u53ef\u4ee5\u7ed3\u5408BeautifulSoup\u6765\u89e3\u6790HTML\u5185\u5bb9\uff0c\u8fd9\u6837\u53ef\u4ee5\u66f4\u65b9\u4fbf\u5730\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
\u83b7\u53d6\u9875\u9762HTML\u5185\u5bb9<\/strong><\/h2>\n
html = driver.page_source<\/p>\n
\u89e3\u6790HTML\u5185\u5bb9<\/strong><\/h2>\n
soup = BeautifulSoup(html, 'html.parser')<\/p>\n
\u83b7\u53d6\u6240\u6709\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
results = soup.find_all('div', class_='g')<\/p>\n
\u904d\u5386\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
for result in results:<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u6807\u9898<\/p>\n
    title = result.find('h3').text<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u94fe\u63a5<\/p>\n
    link = result.find('a')['href']<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u63cf\u8ff0<\/p>\n
    description = result.find('span', class_='st').text<\/p>\n
    print(f'Title: {title}')<\/p>\n
    print(f'Link: {link}')<\/p>\n
    print(f'Description: {description}')<\/p>\n
    print('-' * 80)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u4f7f\u7528Google Custom Search API<\/h3>\n<\/p>\n
\u5982\u679c\u4f60\u4e0d\u60f3\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528Google Custom Search API\u3002\u4f60\u9700\u8981\u5148\u521b\u5efa\u4e00\u4e2a\u81ea\u5b9a\u4e49\u641c\u7d22\u5f15\u64ce\uff0c\u5e76\u83b7\u53d6API\u5bc6\u94a5\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
\u8bbe\u7f6eAPI\u5bc6\u94a5\u548c\u641c\u7d22\u5f15\u64ceID<\/strong><\/h2>\n
api_key = 'YOUR_API_KEY'<\/p>\n
search_engine_id = 'YOUR_SEARCH_ENGINE_ID'<\/p>\n
\u8bbe\u7f6e\u641c\u7d22\u5173\u952e\u8bcd<\/strong><\/h2>\n
query = 'Python web scraping'<\/p>\n
\u6784\u5efaAPI\u8bf7\u6c42URL<\/strong><\/h2>\n
url = f'https:\/\/www.googleapis.com\/customsearch\/v1?q={query}&key={api_key}&cx={search_engine_id}'<\/p>\n
\u53d1\u9001API\u8bf7\u6c42<\/strong><\/h2>\n
response = requests.get(url)<\/p>\n
\u89e3\u6790API\u54cd\u5e94<\/strong><\/h2>\n
data = response.json()<\/p>\n
\u904d\u5386\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
for item in data['items']:<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u6807\u9898<\/p>\n
    title = item['title']<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u94fe\u63a5<\/p>\n
    link = item['link']<\/p>\n
    # \u83b7\u53d6\u7ed3\u679c\u63cf\u8ff0<\/p>\n
    description = item['snippet']<\/p>\n
    print(f'Title: {title}')<\/p>\n
    print(f'Link: {link}')<\/p>\n
    print(f'Description: {description}')<\/p>\n
    print('-' * 80)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u4f7f\u7528Scrapy\u6846\u67b6<\/h3>\n<\/p>\n
Scrapy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u5b83\u53ef\u4ee5\u9ad8\u6548\u5730\u6293\u53d6\u548c\u89e3\u6790\u7f51\u9875\u6570\u636e\u3002\u4f7f\u7528Scrapy\uff0c\u4f60\u53ef\u4ee5\u66f4\u7075\u6d3b\u5730\u5904\u7406\u5927\u89c4\u6a21\u722c\u53d6\u9700\u6c42\u3002<\/p>\n<\/p>\n
import scrapy<\/p>\n
class GoogleSpider(scrapy.Spider):<\/p>\n
    name = "google_spider"<\/p>\n
    allowed_domAI<\/a>ns = ["google.com"]<\/p>\n
    start_urls = ['https:\/\/www.google.com\/search?q=Python+web+scraping']<\/p>\n
    def parse(self, response):<\/p>\n
        # \u83b7\u53d6\u6240\u6709\u641c\u7d22\u7ed3\u679c<\/p>\n
        results = response.xpath('\/\/div[@class="g"]')<\/p>\n
        for result in results:<\/p>\n
            # \u83b7\u53d6\u7ed3\u679c\u6807\u9898<\/p>\n
            title = result.xpath('.\/\/h3\/text()').get()<\/p>\n
            # \u83b7\u53d6\u7ed3\u679c\u94fe\u63a5<\/p>\n
            link = result.xpath('.\/\/a\/@href').get()<\/p>\n
            # \u83b7\u53d6\u7ed3\u679c\u63cf\u8ff0<\/p>\n
            description = result.xpath('.\/\/span[@class="st"]\/text()').get()<\/p>\n
            yield {<\/p>\n
                'title': title,<\/p>\n
                'link': link,<\/p>\n
                'description': description<\/p>\n
            }<\/p>\n
        # \u83b7\u53d6\u4e0b\u4e00\u9875\u94fe\u63a5<\/p>\n
        next_page = response.xpath('\/\/a[@id="pnnext"]\/@href').get()<\/p>\n
        if next_page:<\/p>\n
            yield scrapy.Request(response.urljoin(next_page), callback=self.parse)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n
\u5728\u722c\u53d6\u8c37\u6b4c\u6570\u636e\u65f6\uff0c\u4f60\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u53cd\u722c\u866b\u673a\u5236\uff0c\u4f8b\u5982CAPTCHA\u9a8c\u8bc1\u3002\u4e3a\u4e86\u7ed5\u8fc7\u8fd9\u4e9b\u673a\u5236\uff0c\u4f60\u53ef\u4ee5\u8003\u8651\u4ee5\u4e0b\u51e0\u79cd\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
    \n
  1. \u589e\u52a0\u8bf7\u6c42\u95f4\u9694<\/strong>\uff1a\u5728\u6bcf\u6b21\u8bf7\u6c42\u4e4b\u95f4\u589e\u52a0\u968f\u673a\u7684\u7b49\u5f85\u65f6\u95f4\uff0c\u4ee5\u6a21\u62df\u4eba\u7c7b\u884c\u4e3a\u3002<\/li>\n
  2. \u4f7f\u7528\u4ee3\u7406<\/strong>\uff1a\u901a\u8fc7\u4ee3\u7406\u670d\u52a1\u5668\u53d1\u9001\u8bf7\u6c42\uff0c\u4ee5\u907f\u514dIP\u88ab\u5c01\u7981\u3002<\/li>\n
  3. \u4f7f\u7528\u7528\u6237\u4ee3\u7406<\/strong>\uff1a\u5728\u8bf7\u6c42\u5934\u4e2d\u8bbe\u7f6e\u4e0d\u540c\u7684\u7528\u6237\u4ee3\u7406\uff0c\u4ee5\u6a21\u62df\u4e0d\u540c\u7684\u6d4f\u89c8\u5668\u548c\u8bbe\u5907\u3002<\/li>\n<\/ol>\n
    from selenium.webdriver.common.by import By<\/p>\n
    from selenium.webdriver.chrome.options import Options<\/p>\n
    import random<\/p>\n
    \u8bbe\u7f6eChrome\u9009\u9879<\/strong><\/h2>\n
    chrome_options = Options()<\/p>\n
    chrome_options.add_argument("--headless")<\/p>\n
    chrome_options.add_argument("--disable-gpu")<\/p>\n
    chrome_options.add_argument("user-agent=Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36")<\/p>\n
    \u8bbe\u7f6e\u4ee3\u7406\u670d\u52a1\u5668<\/strong><\/h2>\n
    chrome_options.add_argument('--proxy-server=http:\/\/your-proxy-server:port')<\/p>\n
    \u8bbe\u7f6eChromeDriver\u8def\u5f84<\/strong><\/h2>\n
    driver = webdriver.Chrome(driver_path, options=chrome_options)<\/p>\n
    \u6253\u5f00\u8c37\u6b4c\u4e3b\u9875<\/strong><\/h2>\n
    driver.get("http:\/\/www.google.com")<\/p>\n
    \u627e\u5230\u641c\u7d22\u8f93\u5165\u6846<\/strong><\/h2>\n
    search_box = driver.find_element(By.NAME, "q")<\/p>\n
    \u8f93\u5165\u641c\u7d22\u5173\u952e\u8bcd\u5e76\u56de\u8f66<\/strong><\/h2>\n
    search_box.send_keys("Python web scraping")<\/p>\n
    search_box.send_keys(Keys.RETURN)<\/p>\n
    \u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/strong><\/h2>\n
    time.sleep(random.randint(2, 5))<\/p>\n
    \u83b7\u53d6\u6240\u6709\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
    results = driver.find_elements(By.XPATH, '\/\/div[@class="g"]')<\/p>\n
    \u904d\u5386\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
    for result in results:<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u6807\u9898<\/p>\n
        title = result.find_element(By.XPATH, '.\/\/h3').text<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u94fe\u63a5<\/p>\n
        link = result.find_element(By.XPATH, '.\/\/a').get_attribute('href')<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u63cf\u8ff0<\/p>\n
        description = result.find_element(By.XPATH, '.\/\/span[@class="st"]').text<\/p>\n
        print(f'Title: {title}')<\/p>\n
        print(f'Link: {link}')<\/p>\n
        print(f'Description: {description}')<\/p>\n
        print('-' * 80)<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u4e5d\u3001\u6570\u636e\u5b58\u50a8\u548c\u5904\u7406<\/h3>\n<\/p>\n
    \u5728\u722c\u53d6\u6570\u636e\u540e\uff0c\u6211\u4eec\u901a\u5e38\u9700\u8981\u5c06\u6570\u636e\u5b58\u50a8\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u5904\u7406\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684pandas\u5e93\u5c06\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u4e2d\uff0c\u6216\u8005\u4f7f\u7528SQLite\u6570\u636e\u5e93\u8fdb\u884c\u5b58\u50a8\u3002<\/p>\n<\/p>\n
    \u4f7f\u7528pandas\u5b58\u50a8\u6570\u636e\u5230CSV\u6587\u4ef6<\/h4>\n<\/p>\n
    import pandas as pd<\/p>\n
    \u521b\u5efa\u4e00\u4e2a\u7a7a\u7684DataFrame<\/strong><\/h2>\n
    df = pd.DataFrame(columns=['Title', 'Link', 'Description'])<\/p>\n
    \u904d\u5386\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
    for result in results:<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u6807\u9898<\/p>\n
        title = result.find_element(By.XPATH, '.\/\/h3').text<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u94fe\u63a5<\/p>\n
        link = result.find_element(By.XPATH, '.\/\/a').get_attribute('href')<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u63cf\u8ff0<\/p>\n
        description = result.find_element(By.XPATH, '.\/\/span[@class="st"]').text<\/p>\n
        # \u6dfb\u52a0\u6570\u636e\u5230DataFrame<\/p>\n
        df = df.append({'Title': title, 'Link': link, 'Description': description}, ignore_index=True)<\/p>\n
    \u5c06DataFrame\u5b58\u50a8\u5230CSV\u6587\u4ef6<\/strong><\/h2>\n
    df.to_csv('google_search_results.csv', index=False)<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u4f7f\u7528SQLite\u6570\u636e\u5e93\u5b58\u50a8\u6570\u636e<\/h4>\n<\/p>\n
    import sqlite3<\/p>\n
    \u8fde\u63a5\u5230SQLite\u6570\u636e\u5e93\uff08\u5982\u679c\u6570\u636e\u5e93\u4e0d\u5b58\u5728\uff0c\u5219\u4f1a\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u6570\u636e\u5e93\uff09<\/strong><\/h2>\n
    conn = sqlite3.connect('google_search_results.db')<\/p>\n
    \u521b\u5efa\u4e00\u4e2aCursor\u5bf9\u8c61<\/strong><\/h2>\n
    cur = conn.cursor()<\/p>\n
    \u521b\u5efa\u4e00\u4e2a\u8868<\/strong><\/h2>\n
    cur.execute('''<\/p>\n
        CREATE TABLE IF NOT EXISTS search_results (<\/p>\n
            id INTEGER PRIMARY KEY,<\/p>\n
            title TEXT,<\/p>\n
            link TEXT,<\/p>\n
            description TEXT<\/p>\n
        )<\/p>\n
    ''')<\/p>\n
    \u904d\u5386\u641c\u7d22\u7ed3\u679c<\/strong><\/h2>\n
    for result in results:<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u6807\u9898<\/p>\n
        title = result.find_element(By.XPATH, '.\/\/h3').text<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u94fe\u63a5<\/p>\n
        link = result.find_element(By.XPATH, '.\/\/a').get_attribute('href')<\/p>\n
        # \u83b7\u53d6\u7ed3\u679c\u63cf\u8ff0<\/p>\n
        description = result.find_element(By.XPATH, '.\/\/span[@class="st"]').text<\/p>\n
        # \u63d2\u5165\u6570\u636e\u5230\u8868\u4e2d<\/p>\n
        cur.execute('''<\/p>\n
            INSERT INTO search_results (title, link, description)<\/p>\n
            VALUES (?, ?, ?)<\/p>\n
        ''', (title, link, description))<\/p>\n
    \u63d0\u4ea4\u4e8b\u52a1<\/strong><\/h2>\n
    conn.commit()<\/p>\n
    \u5173\u95ed\u8fde\u63a5<\/strong><\/h2>\n
    conn.close()<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u5341\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
    \u4f7f\u7528Python\u5728\u8c37\u6b4c\u4e0a\u722c\u6570\u636e\u7684\u65b9\u6cd5\u591a\u79cd\u591a\u6837\uff0c\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u4f18\u7f3a\u70b9\u3002Selenium\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u5b83\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u884c\u4e3a\uff0c\u7ed5\u8fc7\u4e00\u4e9b\u53cd\u722c\u866b\u673a\u5236\uff1bBeautifulSoup\u53ef\u4ee5\u9ad8\u6548\u5730\u89e3\u6790HTML\u5185\u5bb9\uff1bGoogle Custom Search API\u53ef\u4ee5\u76f4\u63a5\u83b7\u53d6\u641c\u7d22\u7ed3\u679c\uff0c\u800c\u4e0d\u9700\u8981\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff1bScrapy\u662f\u4e00\u4e2a\u9ad8\u6548\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u5927\u89c4\u6a21\u722c\u53d6\u9700\u6c42\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u4f60\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u5e76\u7ed3\u5408\u591a\u79cd\u6280\u672f\u624b\u6bb5\uff0c\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\uff0c\u786e\u4fdd\u6570\u636e\u722c\u53d6\u7684\u7a33\u5b9a\u6027\u548c\u9ad8\u6548\u6027\u3002\u6700\u540e\uff0c\u5c06\u722c\u53d6\u7684\u6570\u636e\u5b58\u50a8\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4fbf\u4e8e\u540e\u7eed\u5904\u7406\u548c\u5206\u6790\u3002<\/p>\n<\/p>\n
    \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
     \u5982\u4f55\u4f7f\u7528Python\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u7684\u57fa\u672c\u6b65\u9aa4\u662f\u4ec0\u4e48\uff1f<\/strong>
    \u5728\u4f7f\u7528Python\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5\u4e00\u4e9b\u5e38\u7528\u7684\u5e93\uff0c\u6bd4\u5982Requests\u548cBeautifulSoup\u3002Requests\u5e93\u53ef\u4ee5\u5e2e\u52a9\u4f60\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u800cBeautifulSoup\u5219\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\u3002\u63a5\u7740\uff0c\u7f16\u5199\u4ee3\u7801\u6765\u8bf7\u6c42\u7279\u5b9a\u7684URL\uff0c\u83b7\u53d6\u9875\u9762\u7684HTML\u6e90\u4ee3\u7801\uff0c\u5e76\u5229\u7528BeautifulSoup\u63d0\u53d6\u4f60\u9700\u8981\u7684\u6570\u636e\uff0c\u6bd4\u5982\u6807\u9898\u3001\u94fe\u63a5\u6216\u5176\u4ed6\u4fe1\u606f\u3002\u6700\u540e\uff0c\u5904\u7406\u548c\u5b58\u50a8\u6293\u53d6\u5230\u7684\u6570\u636e\uff0c\u53ef\u80fd\u4f1a\u9009\u62e9\u5c06\u5176\u4fdd\u5b58\u5230CSV\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u3002<\/p>\n
    \u5728\u722c\u53d6\u8c37\u6b4c\u641c\u7d22\u7ed3\u679c\u65f6\uff0c\u6709\u54ea\u4e9b\u9700\u8981\u6ce8\u610f\u7684\u4e8b\u9879\uff1f<\/strong>
    \u5f53\u722c\u53d6\u8c37\u6b4c\u641c\u7d22\u7ed3\u679c\u65f6\uff0c\u9700\u8981\u9075\u5faa\u8c37\u6b4c\u7684\u4f7f\u7528\u6761\u6b3e\uff0c\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u5730\u53d1\u9001\u8bf7\u6c42\uff0c\u4ee5\u514d\u88ab\u89c6\u4e3a\u6076\u610f\u884c\u4e3a\u800c\u88ab\u5c01\u7981IP\u3002\u4f7f\u7528\u4ee3\u7406IP\u548c\u9002\u5f53\u7684\u8bf7\u6c42\u95f4\u9694\u53ef\u4ee5\u5e2e\u52a9\u51cf\u5c11\u88ab\u5c01\u7684\u98ce\u9669\u3002\u6b64\u5916\uff0c\u8c37\u6b4c\u7684\u641c\u7d22\u7ed3\u679c\u9875\u9762\u662f\u52a8\u6001\u751f\u6210\u7684\uff0c\u53ef\u80fd\u9700\u8981\u4f7f\u7528Selenium\u7b49\u5de5\u5177\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u6765\u83b7\u53d6\u6570\u636e\u3002\u786e\u4fdd\u9075\u5faarobots.txt\u6587\u4ef6\u4e2d\u7684\u89c4\u5219\uff0c\u4e86\u89e3\u54ea\u4e9b\u9875\u9762\u5141\u8bb8\u722c\u53d6\u3002<\/p>\n
    \u5982\u4f55\u5904\u7406\u6293\u53d6\u5230\u7684\u6570\u636e\u4ee5\u4fbf\u8fdb\u884c\u5206\u6790\uff1f<\/strong>
    \u6293\u53d6\u5230\u7684\u6570\u636e\u901a\u5e38\u662f\u4ee5\u6587\u672c\u5f62\u5f0f\u5b58\u5728\uff0c\u9996\u5148\u9700\u8981\u5bf9\u5176\u8fdb\u884c\u6e05\u6d17\uff0c\u53bb\u9664\u591a\u4f59\u7684\u7a7a\u683c\u3001\u7279\u6b8a\u5b57\u7b26\u53caHTML\u6807\u7b7e\u7b49\u3002\u53ef\u4ee5\u4f7f\u7528Pandas\u5e93\u5c06\u6570\u636e\u52a0\u8f7d\u5230DataFrame\u4e2d\uff0c\u4fbf\u4e8e\u8fdb\u4e00\u6b65\u5206\u6790\u3002\u63a5\u4e0b\u6765\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684\u6570\u636e\u5206\u6790\u5e93\uff0c\u5982NumPy\u548cMatplotlib\uff0c\u5bf9\u6570\u636e\u8fdb\u884c\u7edf\u8ba1\u548c\u53ef\u89c6\u5316\u5206\u6790\uff0c\u5e2e\u52a9\u4f60\u4ece\u6293\u53d6\u7684\u6570\u636e\u4e2d\u63d0\u53d6\u6709\u4ef7\u503c\u7684\u4fe1\u606f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u5728\u8c37\u6b4c\u4e0a\u722c\u6570\u636e\u6709\u51e0\u79cd\u65b9\u6cd5\uff1a\u4f7f\u7528Selenium\u81ea\u52a8\u5316\u6d4f\u89c8\u5668\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790 […]","protected":false},"author":3,"featured_media":1026604,"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\/1026594"}],"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=1026594"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1026594\/revisions"}],"predecessor-version":[{"id":1026607,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1026594\/revisions\/1026607"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1026604"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1026594"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1026594"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1026594"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}