{"id":1187441,"date":"2025-01-15T20:05:33","date_gmt":"2025-01-15T12:05:33","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1187441.html"},"modified":"2025-01-15T20:05:36","modified_gmt":"2025-01-15T12:05:36","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e6%8a%93%e5%8f%96%e5%8a%a8%e6%80%81%e9%a1%b5","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1187441.html","title":{"rendered":"\u5982\u4f55\u7528python\u6293\u53d6\u52a8\u6001\u9875"},"content":{"rendered":"

\"\u5982\u4f55\u7528python\u6293\u53d6\u52a8\u6001\u9875\"<\/p>\n

\u4f7f\u7528Selenium\u3001\u4f7f\u7528Requests\u5e93\u7ed3\u5408BeautifulSoup\u3001\u4f7f\u7528Scrapy<\/strong><\/p>\n<\/p>\n

\u4f7f\u7528Selenium\u662f\u6293\u53d6\u52a8\u6001\u9875\u9762\u7684\u5e38\u89c1\u65b9\u6cd5\u4e4b\u4e00\u3002\u5b83\u80fd\u591f\u6a21\u62df\u7528\u6237\u884c\u4e3a\uff0c\u4e0eJavaScript\u751f\u6210\u7684\u52a8\u6001\u5185\u5bb9\u8fdb\u884c\u4ea4\u4e92\u3002\u56e0\u6b64\uff0cSelenium\u975e\u5e38\u9002\u5408\u4e8e\u6293\u53d6\u90a3\u4e9b\u9700\u8981\u7528\u6237\u64cd\u4f5c\u624d\u80fd\u52a0\u8f7d\u7684\u5185\u5bb9\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u4f7f\u7528Selenium\u6765\u6293\u53d6\u52a8\u6001\u9875\u9762\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528Selenium<\/h3>\n<\/p>\n

1.1 \u5b89\u88c5Selenium\u548c\u6d4f\u89c8\u5668\u9a71\u52a8<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5Selenium\u5e93\u548c\u6d4f\u89c8\u5668\u9a71\u52a8\u7a0b\u5e8f\uff08\u5982ChromeDriver\uff09\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5Selenium\uff1a<\/p>\n<\/p>\n

pip install selenium<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u7136\u540e\uff0c\u4e0b\u8f7d\u4e0e\u60a8\u6d4f\u89c8\u5668\u7248\u672c\u5339\u914d\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u5e76\u5c06\u5176\u6dfb\u52a0\u5230\u7cfb\u7edf\u8def\u5f84\u4e2d\u3002<\/p>\n<\/p>\n
1.2 \u542f\u52a8\u6d4f\u89c8\u5668\u5e76\u52a0\u8f7d\u9875\u9762<\/h4>\n<\/p>\n
\u4e0b\u9762\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff0c\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528Selenium\u542f\u52a8\u6d4f\u89c8\u5668\u5e76\u52a0\u8f7d\u4e00\u4e2a\u52a8\u6001\u9875\u9762\uff1a<\/p>\n<\/p>\n
from selenium import webdriver<\/p>\n
from selenium.webdriver.common.by import By<\/p>\n
from selenium.webdriver.support.ui import WebDriverWAI<\/a>t<\/p>\n
from selenium.webdriver.support import expected_conditions as EC<\/p>\n
\u542f\u52a8Chrome\u6d4f\u89c8\u5668<\/strong><\/h2>\n
driver = webdriver.Chrome()<\/p>\n
\u8bbf\u95ee\u76ee\u6807\u7f51\u5740<\/strong><\/h2>\n
driver.get("https:\/\/example.com")<\/p>\n
\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210<\/strong><\/h2>\n
element = WebDriverWait(driver, 10).until(<\/p>\n
    EC.presence_of_element_located((By.ID, "element_id"))<\/p>\n
)<\/p>\n
\u83b7\u53d6\u9875\u9762\u5185\u5bb9<\/strong><\/h2>\n
html = driver.page_source<\/p>\n
\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n
driver.quit()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528WebDriverWait<\/code>\u7b49\u5f85\u9875\u9762\u4e0a\u7684\u67d0\u4e2a\u5143\u7d20\u52a0\u8f7d\u5b8c\u6210\uff0c\u7136\u540e\u83b7\u53d6\u9875\u9762\u7684HTML\u6e90\u4ee3\u7801\u3002<\/p>\n<\/p>\n
1.3 \u5904\u7406\u52a8\u6001\u5185\u5bb9<\/h4>\n<\/p>\n
\u6709\u65f6\uff0c\u52a8\u6001\u5185\u5bb9\u53ef\u80fd\u9700\u8981\u7528\u6237\u64cd\u4f5c\u624d\u80fd\u52a0\u8f7d\uff0c\u4f8b\u5982\u70b9\u51fb\u6309\u94ae\u6216\u6eda\u52a8\u9875\u9762\u3002Selenium\u53ef\u4ee5\u6a21\u62df\u8fd9\u4e9b\u7528\u6237\u64cd\u4f5c\uff1a<\/p>\n<\/p>\n
# \u70b9\u51fb\u6309\u94ae<\/p>\n
button = driver.find_element(By.ID, "button_id")<\/p>\n
button.click()<\/p>\n
\u6eda\u52a8\u9875\u9762<\/strong><\/h2>\n
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\uff0c\u60a8\u53ef\u4ee5\u4e0e\u9875\u9762\u8fdb\u884c\u5404\u79cd\u4ea4\u4e92\uff0c\u5e76\u6293\u53d6JavaScript\u751f\u6210\u7684\u52a8\u6001\u5185\u5bb9\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Requests\u5e93\u7ed3\u5408BeautifulSoup<\/h3>\n<\/p>\n
2.1 \u5b89\u88c5Requests\u548cBeautifulSoup<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u60a8\u9700\u8981\u5b89\u88c5Requests\u548cBeautifulSoup\u5e93\uff1a<\/p>\n<\/p>\n
pip install requests<\/p>\n
pip install beautifulsoup4<\/p>\n
<\/code><\/pre>\n<\/p>\n
2.2 \u53d1\u9001\u8bf7\u6c42\u5e76\u89e3\u6790\u5185\u5bb9<\/h4>\n<\/p>\n
\u6709\u4e9b\u52a8\u6001\u9875\u9762\u7684\u6570\u636e\u53ef\u4ee5\u901a\u8fc7\u5206\u6790\u7f51\u7edc\u8bf7\u6c42\u6765\u83b7\u53d6\u3002\u60a8\u53ef\u4ee5\u4f7f\u7528Requests\u5e93\u53d1\u9001\u8bf7\u6c42\uff0c\u5e76\u4f7f\u7528BeautifulSoup\u89e3\u6790\u8fd4\u56de\u7684\u5185\u5bb9\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
\u53d1\u9001GET\u8bf7\u6c42<\/strong><\/h2>\n
response = requests.get("https:\/\/example.com\/api\/data")<\/p>\n
\u89e3\u6790\u8fd4\u56de\u7684\u5185\u5bb9<\/strong><\/h2>\n
soup = BeautifulSoup(response.content, "html.parser")<\/p>\n
\u63d0\u53d6\u6240\u9700\u6570\u636e<\/strong><\/h2>\n
data = soup.find_all("div", class_="data_class")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u79cd\u65b9\u6cd5\u9002\u7528\u4e8e\u901a\u8fc7API\u6216\u76f4\u63a5\u5728HTML\u4e2d\u8fd4\u56de\u6570\u636e\u7684\u52a8\u6001\u9875\u9762\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528Scrapy<\/h3>\n<\/p>\n
Scrapy\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u7528\u4e8e\u5927\u89c4\u6a21\u7684\u6570\u636e\u6293\u53d6\u3002\u5b83\u652f\u6301\u5f02\u6b65\u5904\u7406\u548c\u591a\u7ebf\u7a0b\uff0c\u80fd\u591f\u9ad8\u6548\u5730\u6293\u53d6\u5927\u91cf\u6570\u636e\u3002<\/p>\n<\/p>\n
3.1 \u5b89\u88c5Scrapy<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u60a8\u9700\u8981\u5b89\u88c5Scrapy\uff1a<\/p>\n<\/p>\n
pip install scrapy<\/p>\n
<\/code><\/pre>\n<\/p>\n
3.2 \u521b\u5efaScrapy\u9879\u76ee<\/h4>\n<\/p>\n
\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u521b\u5efa\u4e00\u4e2a\u65b0\u7684Scrapy\u9879\u76ee\uff1a<\/p>\n<\/p>\n
scrapy startproject myproject<\/p>\n
<\/code><\/pre>\n<\/p>\n
3.3 \u5b9a\u4e49\u722c\u866b<\/h4>\n<\/p>\n
\u5728\u9879\u76ee\u76ee\u5f55\u4e2d\uff0c\u5b9a\u4e49\u4e00\u4e2a\u722c\u866b\u6765\u6293\u53d6\u52a8\u6001\u9875\u9762\uff1a<\/p>\n<\/p>\n
import scrapy<\/p>\n
class MySpider(scrapy.Spider):<\/p>\n
    name = "myspider"<\/p>\n
    start_urls = ["https:\/\/example.com"]<\/p>\n
    def parse(self, response):<\/p>\n
        # \u63d0\u53d6\u6240\u9700\u6570\u636e<\/p>\n
        data = response.css(".data_class").getall()<\/p>\n
        yield {"data": data}<\/p>\n
        # \u5904\u7406\u5206\u9875\u6216\u52a8\u6001\u5185\u5bb9<\/p>\n
        next_page = response.css("a.next::attr(href)").get()<\/p>\n
        if next_page:<\/p>\n
            yield response.follow(next_page, self.parse)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3.4 \u8fd0\u884c\u722c\u866b<\/h4>\n<\/p>\n
\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fd0\u884c\u722c\u866b\uff1a<\/p>\n<\/p>\n
scrapy crawl myspider<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7Scrapy\uff0c\u60a8\u53ef\u4ee5\u8f7b\u677e\u5730\u6293\u53d6\u5927\u89c4\u6a21\u7684\u52a8\u6001\u5185\u5bb9\uff0c\u5e76\u5c06\u6570\u636e\u4fdd\u5b58\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u3002<\/p>\n<\/p>\n
\u56db\u3001\u4f7f\u7528\u4ee3\u7406\u548c\u53cd\u53cd\u722c\u6280\u672f<\/h3>\n<\/p>\n
\u6293\u53d6\u52a8\u6001\u9875\u9762\u65f6\uff0c\u60a8\u53ef\u80fd\u4f1a\u9047\u5230\u7f51\u7ad9\u7684\u53cd\u722c\u63aa\u65bd\uff0c\u5982IP\u5c01\u7981\u548c\u9a8c\u8bc1\u7801\u3002\u4f7f\u7528\u4ee3\u7406\u548c\u53cd\u53cd\u722c\u6280\u672f\u53ef\u4ee5\u5e2e\u52a9\u60a8\u7ed5\u8fc7\u8fd9\u4e9b\u9650\u5236\u3002<\/p>\n<\/p>\n
4.1 \u4f7f\u7528\u4ee3\u7406<\/h4>\n<\/p>\n
\u60a8\u53ef\u4ee5\u4f7f\u7528\u4ee3\u7406\u670d\u52a1\u5668\u6765\u9690\u85cf\u60a8\u7684\u771f\u5b9eIP\u5730\u5740\uff0c\u5e76\u5206\u6563\u8bf7\u6c42\u4ee5\u907f\u514d\u88ab\u5c01\u7981\uff1a<\/p>\n<\/p>\n
proxies = {<\/p>\n
    "http": "http:\/\/your_proxy_ip:port",<\/p>\n
    "https": "https:\/\/your_proxy_ip:port"<\/p>\n
}<\/p>\n
response = requests.get("https:\/\/example.com", proxies=proxies)<\/p>\n
<\/code><\/pre>\n<\/p>\n
4.2 \u6a21\u62df\u7528\u6237\u884c\u4e3a<\/h4>\n<\/p>\n
\u6a21\u62df\u7528\u6237\u884c\u4e3a\u53ef\u4ee5\u5e2e\u52a9\u60a8\u907f\u514d\u88ab\u68c0\u6d4b\u4e3a\u722c\u866b\u3002\u4f8b\u5982\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528Selenium\u968f\u673a\u7b49\u5f85\u4e00\u6bb5\u65f6\u95f4\uff0c\u6216\u6a21\u62df\u9f20\u6807\u79fb\u52a8\u548c\u70b9\u51fb\uff1a<\/p>\n<\/p>\n
import time<\/p>\n
import random<\/p>\n
\u968f\u673a\u7b49\u5f85\u4e00\u6bb5\u65f6\u95f4<\/strong><\/h2>\n
time.sleep(random.uniform(1, 5))<\/p>\n
\u6a21\u62df\u9f20\u6807\u79fb\u52a8\u548c\u70b9\u51fb<\/strong><\/h2>\n
from selenium.webdriver.common.action_chains import ActionChains<\/p>\n
actions = ActionChains(driver)<\/p>\n
actions.move_to_element(button).click().perform()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u7ed3\u5408\u4f7f\u7528Selenium\u3001Requests\u5e93\u3001BeautifulSoup\u3001Scrapy\u3001\u4ee3\u7406\u548c\u53cd\u53cd\u722c\u6280\u672f\uff0c\u60a8\u53ef\u4ee5\u6709\u6548\u5730\u6293\u53d6\u5404\u79cd\u52a8\u6001\u9875\u9762\uff0c\u5e76\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u638c\u63e1\u8fd9\u4e9b\u5de5\u5177\u548c\u6280\u5de7\uff0c\u5c06\u5e2e\u52a9\u60a8\u5728\u6570\u636e\u6293\u53d6\u548c\u7f51\u7edc\u722c\u866b\u9886\u57df\u53d6\u5f97\u6210\u529f\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u52a8\u6001\u7f51\u9875\u6293\u53d6\u7684\u57fa\u7840\u77e5\u8bc6\u662f\u4ec0\u4e48\uff1f<\/strong>
\u52a8\u6001\u7f51\u9875\u901a\u5e38\u4f7f\u7528JavaScript\u52a0\u8f7d\u5185\u5bb9\uff0c\u8fd9\u610f\u5473\u7740\u5728\u7f51\u9875\u521d\u59cb\u52a0\u8f7d\u65f6\uff0c\u90e8\u5206\u4fe1\u606f\u53ef\u80fd\u5e76\u672a\u5448\u73b0\u3002\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u4f7f\u7528\u4f20\u7edf\u7684\u9759\u6001\u7f51\u9875\u6293\u53d6\u5de5\u5177\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u6240\u9700\u7684\u6570\u636e\u3002Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5e93\uff0c\u5982Selenium\u548cRequests-HTML\uff0c\u53ef\u4ee5\u6709\u6548\u6293\u53d6\u52a8\u6001\u7f51\u9875\u3002\u4e86\u89e3\u8fd9\u4e9b\u5e93\u7684\u57fa\u672c\u7528\u6cd5\u548c\u7279\u6027\u662f\u6210\u529f\u6293\u53d6\u7684\u5173\u952e\u3002<\/p>\n
\u4f7f\u7528Selenium\u6293\u53d6\u52a8\u6001\u7f51\u9875\u7684\u6b65\u9aa4\u6709\u54ea\u4e9b\uff1f<\/strong>
\u6293\u53d6\u52a8\u6001\u7f51\u9875\u65f6\uff0c\u4f7f\u7528Selenium\u662f\u4e00\u4e2a\u5e38\u89c1\u9009\u62e9\u3002\u9996\u5148\uff0c\u60a8\u9700\u8981\u5b89\u88c5Selenium\u5e93\u5e76\u4e0b\u8f7d\u76f8\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\u3002\u63a5\u7740\uff0c\u60a8\u53ef\u4ee5\u901a\u8fc7\u7f16\u5199Python\u4ee3\u7801\u542f\u52a8\u6d4f\u89c8\u5668\uff0c\u8bbf\u95ee\u76ee\u6807\u7f51\u7ad9\uff0c\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\uff0c\u6700\u540e\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u4f7f\u7528Selenium\u7684\u4f18\u52bf\u5728\u4e8e\u5b83\u80fd\u591f\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff0c\u5904\u7406\u9875\u9762\u4e0a\u590d\u6742\u7684\u4ea4\u4e92\u548c\u52a0\u8f7d\u3002<\/p>\n
\u6293\u53d6\u52a8\u6001\u7f51\u9875\u65f6\u9047\u5230\u53cd\u722c\u866b\u673a\u5236\u8be5\u5982\u4f55\u5e94\u5bf9\uff1f<\/strong>
\u8bb8\u591a\u7f51\u7ad9\u4f1a\u5b9e\u73b0\u53cd\u722c\u866b\u673a\u5236\u6765\u4fdd\u62a4\u5176\u6570\u636e\u3002\u8981\u6709\u6548\u5e94\u5bf9\u8fd9\u4e9b\u6311\u6218\uff0c\u53ef\u4ee5\u91c7\u53d6\u51e0\u79cd\u7b56\u7565\u3002\u589e\u52a0\u8bf7\u6c42\u7684\u95f4\u9694\u65f6\u95f4\uff0c\u968f\u673a\u5316\u8bf7\u6c42\u5934\uff0c\u4f7f\u7528\u4ee3\u7406IP\uff0c\u6216\u662f\u5b9e\u73b0\u767b\u5f55\u72b6\u6001\u4fdd\u6301\u7b49\u65b9\u6cd5\uff0c\u90fd\u80fd\u591f\u964d\u4f4e\u88ab\u68c0\u6d4b\u5230\u7684\u98ce\u9669\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u6d4f\u89c8\u5668\u6a21\u62df\u5de5\u5177\u5982Selenium\u80fd\u591f\u66f4\u597d\u5730\u6a21\u62df\u6b63\u5e38\u7528\u6237\u884c\u4e3a\uff0c\u4ece\u800c\u7ed5\u8fc7\u4e00\u4e9b\u7b80\u5355\u7684\u53cd\u722c\u866b\u63aa\u65bd\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Selenium\u3001\u4f7f\u7528Requests\u5e93\u7ed3\u5408BeautifulSoup\u3001\u4f7f\u7528Scrapy \u4f7f\u7528Seleni […]","protected":false},"author":3,"featured_media":1187448,"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\/1187441"}],"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=1187441"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1187441\/revisions"}],"predecessor-version":[{"id":1187450,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1187441\/revisions\/1187450"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1187448"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1187441"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1187441"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1187441"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}