{"id":1153569,"date":"2025-01-13T17:40:24","date_gmt":"2025-01-13T09:40:24","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1153569.html"},"modified":"2025-01-13T17:40:27","modified_gmt":"2025-01-13T09:40:27","slug":"python%e5%a6%82%e4%bd%95%e9%80%9a%e8%bf%87%e9%93%be%e6%8e%a5%e7%bf%bb%e9%a1%b5","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1153569.html","title":{"rendered":"python\u5982\u4f55\u901a\u8fc7\u94fe\u63a5\u7ffb\u9875"},"content":{"rendered":"

\"python\u5982\u4f55\u901a\u8fc7\u94fe\u63a5\u7ffb\u9875\"<\/p>\n

Python\u901a\u8fc7\u94fe\u63a5\u7ffb\u9875\u7684\u65b9\u6cd5\u6709\u5f88\u591a\uff0c\u4e3b\u8981\u5305\u62ec\uff1a\u4f7f\u7528Requests\u5e93\u8bf7\u6c42\u9875\u9762\u3001BeautifulSoup\u89e3\u6790HTML\u3001Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u3001Scrapy\u722c\u866b\u6846\u67b6\u7b49\u3002<\/strong><\/p>\n<\/p>\n

\u5176\u4e2d\uff0c\u4f7f\u7528Requests\u5e93\u548cBeautifulSoup\u89e3\u6790HTML\u662f\u4e00\u79cd\u5e38\u89c1\u4e14\u9ad8\u6548\u7684\u65b9\u6cd5\u3002<\/strong>\u5728\u8fd9\u79cd\u65b9\u6cd5\u4e2d\uff0c\u4f60\u9700\u8981\u627e\u5230\u9875\u9762\u4e2d\u7528\u4e8e\u7ffb\u9875\u7684\u94fe\u63a5\u6216\u8005\u6309\u94ae\uff0c\u901a\u8fc7\u89e3\u6790\u7f51\u9875HTML\u6765\u83b7\u53d6\u8fd9\u4e9b\u94fe\u63a5\uff0c\u7136\u540e\u8fdb\u884c\u8bf7\u6c42\u83b7\u53d6\u4e0b\u4e00\u9875\u5185\u5bb9\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u79cd\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u4e00\u3001REQUESTS\u5e93\u4e0eBEAUTIFULSOUP\u89e3\u6790HTML<\/h2>\n<\/p>\n

1\u3001Requests\u5e93\u7b80\u4ecb<\/h3>\n<\/p>\n

Requests\u5e93\u662f\u4e00\u4e2a\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u7684Python\u5e93\uff0c\u4f7f\u7528\u5b83\u53ef\u4ee5\u8f7b\u677e\u5730\u4e0e\u7f51\u9875\u8fdb\u884c\u4ea4\u4e92\u3002\u5b83\u63d0\u4f9b\u4e86\u4e00\u4e9b\u7b80\u5355\u7684API\uff0c\u53ef\u4ee5\u8ba9\u4f60\u53d1\u9001GET\u3001POST\u7b49\u8bf7\u6c42\uff0c\u5e76\u83b7\u53d6\u54cd\u5e94\u6570\u636e\u3002<\/p>\n<\/p>\n

2\u3001BeautifulSoup\u7b80\u4ecb<\/h3>\n<\/p>\n

BeautifulSoup\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684Python\u5e93\u3002\u5b83\u63d0\u4f9b\u4e86Pythonic\u7684\u65b9\u5f0f\u6765\u5bfc\u822a\u3001\u641c\u7d22\u548c\u4fee\u6539\u89e3\u6790\u6811\u3002\u4f7f\u7528BeautifulSoup\uff0c\u4f60\u53ef\u4ee5\u8f7b\u677e\u5730\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n

3\u3001\u5177\u4f53\u5b9e\u73b0\u6b65\u9aa4<\/h3>\n<\/p>\n

1. \u5b89\u88c5\u6240\u9700\u5e93<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5Requests\u5e93\u548cBeautifulSoup\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528pip\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install requests<\/p>\n
pip install beautifulsoup4<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u521d\u59cb\u9875\u9762<\/h4>\n<\/p>\n
\u4f7f\u7528Requests\u5e93\u53d1\u9001\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'https:\/\/example.com'  # \u66ff\u6362\u4e3a\u76ee\u6807\u7f51\u7ad9\u7684URL<\/p>\n
response = requests.get(url)<\/p>\n
html_content = response.content<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u89e3\u6790HTML\u83b7\u53d6\u7ffb\u9875\u94fe\u63a5<\/h4>\n<\/p>\n
\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\uff0c\u627e\u5230\u7ffb\u9875\u7684\u94fe\u63a5\uff1a<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n
next_page_link = soup.find('a', {'class': 'next'})['href']  # \u6839\u636e\u5b9e\u9645\u60c5\u51b5\u4fee\u6539\u9009\u62e9\u5668<\/p>\n
<\/code><\/pre>\n<\/p>\n
4. \u5faa\u73af\u8bf7\u6c42\u83b7\u53d6\u6240\u6709\u9875\u9762<\/h4>\n<\/p>\n
\u901a\u8fc7\u5faa\u73af\u8bf7\u6c42\u83b7\u53d6\u6240\u6709\u9875\u9762\u7684\u5185\u5bb9\uff1a<\/p>\n<\/p>\n
while next_page_link:<\/p>\n
    response = requests.get(next_page_link)<\/p>\n
    html_content = response.content<\/p>\n
    soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n
    # \u5904\u7406\u5f53\u524d\u9875\u9762\u5185\u5bb9<\/p>\n
    # ...<\/p>\n
    # \u83b7\u53d6\u4e0b\u4e00\u9875\u94fe\u63a5<\/p>\n
    next_page_link = soup.find('a', {'class': 'next'})['href'] if soup.find('a', {'class': 'next'}) else None<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001SELENIUM\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c<\/h2>\n<\/p>\n
1\u3001Selenium\u7b80\u4ecb<\/h3>\n<\/p>\n
Selenium\u662f\u4e00\u4e2a\u7528\u4e8e\u81ea\u52a8\u5316Web\u6d4f\u89c8\u5668\u64cd\u4f5c\u7684\u5de5\u5177\u3002\u5b83\u63d0\u4f9b\u4e86\u591a\u79cd\u8bed\u8a00\u7684\u63a5\u53e3\uff0c\u5176\u4e2d\u5305\u62ecPython\u3002\u4f7f\u7528Selenium\uff0c\u4f60\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u5728\u6d4f\u89c8\u5668\u4e2d\u7684\u64cd\u4f5c\uff0c\u5982\u70b9\u51fb\u3001\u8f93\u5165\u7b49\uff0c\u9002\u7528\u4e8e\u5904\u7406\u9700\u8981JavaScript\u6e32\u67d3\u7684\u52a8\u6001\u7f51\u9875\u3002<\/p>\n<\/p>\n
2\u3001\u5b89\u88c5\u4e0e\u8bbe\u7f6e<\/h3>\n<\/p>\n
\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5Selenium\u5e93\u548c\u6d4f\u89c8\u5668\u9a71\u52a8\uff08\u5982ChromeDriver\uff09\uff1a<\/p>\n<\/p>\n
pip install selenium<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0b\u8f7d\u76f8\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u5e76\u5c06\u5176\u8def\u5f84\u6dfb\u52a0\u5230\u7cfb\u7edf\u73af\u5883\u53d8\u91cf\u4e2d\u3002<\/p>\n<\/p>\n
3\u3001\u5177\u4f53\u5b9e\u73b0\u6b65\u9aa4<\/h3>\n<\/p>\n
1. \u5bfc\u5165Selenium\u5e93\u5e76\u542f\u52a8\u6d4f\u89c8\u5668<\/h4>\n<\/p>\n
from selenium import webdriver<\/p>\n
driver = webdriver.Chrome()  # \u6216\u8005\u4f7f\u7528\u5176\u4ed6\u6d4f\u89c8\u5668\u9a71\u52a8<\/p>\n
driver.get('https:\/\/example.com')  # \u66ff\u6362\u4e3a\u76ee\u6807\u7f51\u7ad9\u7684URL<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u67e5\u627e\u7ffb\u9875\u6309\u94ae\u5e76\u70b9\u51fb<\/h4>\n<\/p>\n
while True:<\/p>\n
    try:<\/p>\n
        next_button = driver.find_element_by_class_name('next')  # \u6839\u636e\u5b9e\u9645\u60c5\u51b5\u4fee\u6539\u9009\u62e9\u5668<\/p>\n
        next_button.click()<\/p>\n
        # \u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/p>\n
        time.sleep(2)<\/p>\n
        # \u5904\u7406\u5f53\u524d\u9875\u9762\u5185\u5bb9<\/p>\n
        # ...<\/p>\n
    except:<\/p>\n
        break<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u5173\u95ed\u6d4f\u89c8\u5668<\/h4>\n<\/p>\n
driver.quit()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001SCRAPY\u6846\u67b6<\/h2>\n<\/p>\n
1\u3001Scrapy\u7b80\u4ecb<\/h3>\n<\/p>\n
Scrapy\u662f\u4e00\u4e2a\u7528\u4e8e\u7f51\u9875\u6293\u53d6\u7684\u5f3a\u5927\u6846\u67b6\u3002\u5b83\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u529f\u80fd\u548c\u7075\u6d3b\u7684\u914d\u7f6e\uff0c\u53ef\u4ee5\u9ad8\u6548\u5730\u6293\u53d6\u548c\u5904\u7406\u7f51\u9875\u6570\u636e\u3002Scrapy\u5177\u6709\u5f3a\u5927\u7684\u6269\u5c55\u80fd\u529b\uff0c\u53ef\u4ee5\u901a\u8fc7\u4e2d\u95f4\u4ef6\u3001\u7ba1\u9053\u7b49\u5b9e\u73b0\u81ea\u5b9a\u4e49\u529f\u80fd\u3002<\/p>\n<\/p>\n
2\u3001\u5b89\u88c5\u4e0e\u914d\u7f6e<\/h3>\n<\/p>\n
\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5Scrapy\uff1a<\/p>\n<\/p>\n
pip install scrapy<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u521b\u5efaScrapy\u9879\u76ee<\/h3>\n<\/p>\n
\u4f7f\u7528Scrapy\u547d\u4ee4\u521b\u5efa\u4e00\u4e2a\u65b0\u9879\u76ee\uff1a<\/p>\n<\/p>\n
scrapy startproject myproject<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u7f16\u5199\u722c\u866b<\/h3>\n<\/p>\n
\u5728\u9879\u76ee\u76ee\u5f55\u4e0b\uff0c\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u722c\u866b\u6587\u4ef6\uff0c\u5e76\u7f16\u5199\u722c\u866b\u903b\u8f91\uff1a<\/p>\n<\/p>\n
import scrapy<\/p>\n
class MySpider(scrapy.Spider):<\/p>\n
    name = 'myspider'<\/p>\n
    start_urls = ['https:\/\/example.com']  # \u66ff\u6362\u4e3a\u76ee\u6807\u7f51\u7ad9\u7684URL<\/p>\n
    def parse(self, response):<\/p>\n
        # \u5904\u7406\u5f53\u524d\u9875\u9762\u5185\u5bb9<\/p>\n
        # ...<\/p>\n
        # \u83b7\u53d6\u4e0b\u4e00\u9875\u94fe\u63a5\u5e76\u8bf7\u6c42<\/p>\n
        next_page_link = response.css('a.next::attr(href)').get()  # \u6839\u636e\u5b9e\u9645\u60c5\u51b5\u4fee\u6539\u9009\u62e9\u5668<\/p>\n
        if next_page_link:<\/p>\n
            yield scrapy.Request(url=next_page_link, callback=self.parse)<\/p>\n
<\/code><\/pre>\n<\/p>\n
5\u3001\u8fd0\u884c\u722c\u866b<\/h3>\n<\/p>\n
\u5728\u9879\u76ee\u76ee\u5f55\u4e0b\uff0c\u4f7f\u7528Scrapy\u547d\u4ee4\u8fd0\u884c\u722c\u866b\uff1a<\/p>\n<\/p>\n
scrapy crawl myspider<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u603b\u7ed3<\/h2>\n<\/p>\n
\u901a\u8fc7\u4e0a\u9762\u7684\u4ecb\u7ecd\uff0c\u6211\u4eec\u53ef\u4ee5\u770b\u5230\uff0cPython\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u5b9e\u73b0\u901a\u8fc7\u94fe\u63a5\u7ffb\u9875\u7684\u529f\u80fd\u3002Requests\u5e93\u548cBeautifulSoup\u89e3\u6790HTML\u662f\u4e00\u79cd\u5e38\u89c1\u4e14\u9ad8\u6548\u7684\u65b9\u6cd5<\/strong>\uff0c\u9002\u7528\u4e8e\u5904\u7406\u9759\u6001\u7f51\u9875\u3002Selenium\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u9002\u7528\u4e8e\u5904\u7406\u52a8\u6001\u7f51\u9875<\/strong>\u3002Scrapy\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u7f51\u9875\u6293\u53d6\u6846\u67b6\uff0c\u9002\u7528\u4e8e\u590d\u6742\u7684\u6293\u53d6\u4efb\u52a1<\/strong>\u3002<\/p>\n<\/p>\n
\u9009\u62e9\u54ea\u79cd\u65b9\u6cd5\u53d6\u51b3\u4e8e\u5177\u4f53\u7684\u9700\u6c42\u548c\u7f51\u9875\u7684\u7279\u70b9\u3002\u5e0c\u671b\u901a\u8fc7\u8fd9\u7bc7\u6587\u7ae0\uff0c\u4f60\u80fd\u591f\u638c\u63e1Python\u901a\u8fc7\u94fe\u63a5\u7ffb\u9875\u7684\u57fa\u672c\u65b9\u6cd5\uff0c\u5e76\u80fd\u591f\u6839\u636e\u5b9e\u9645\u60c5\u51b5\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u548c\u65b9\u6cd5\u6765\u5b9e\u73b0\u81ea\u5df1\u7684\u9700\u6c42\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u5b9e\u73b0\u7f51\u9875\u7ffb\u9875\u529f\u80fd\uff1f<\/strong>
\u5728Python\u4e2d\u5b9e\u73b0\u7f51\u9875\u7ffb\u9875\u901a\u5e38\u9700\u8981\u4f7f\u7528\u7f51\u7edc\u8bf7\u6c42\u5e93\uff08\u5982Requests\uff09\u548c\u89e3\u6790\u5e93\uff08\u5982BeautifulSoup\u6216lxml\uff09\u3002\u9996\u5148\uff0c\u901a\u8fc7Requests\u5e93\u53d1\u9001GET\u8bf7\u6c42\u83b7\u53d6\u9875\u9762\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\uff0c\u67e5\u627e\u7ffb\u9875\u7684\u94fe\u63a5\u6216\u6309\u94ae\uff0c\u83b7\u53d6\u5176URL\u5e76\u518d\u6b21\u53d1\u9001\u8bf7\u6c42\uff0c\u4ee5\u6b64\u5b9e\u73b0\u7ffb\u9875\u3002<\/p>\n
\u6709\u54ea\u4e9bPython\u5e93\u53ef\u4ee5\u5e2e\u52a9\u5b9e\u73b0\u7ffb\u9875\uff1f<\/strong>
\u5e38\u7528\u7684\u5e93\u5305\u62ecRequests\u548cBeautifulSoup\uff0cRequests\u8d1f\u8d23\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u800cBeautifulSoup\u5219\u7528\u4e8e\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3002\u5bf9\u4e8e\u52a8\u6001\u52a0\u8f7d\u7684\u9875\u9762\uff0cSelenium\u4e5f\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u9009\u62e9\uff0c\u5b83\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff0c\u81ea\u52a8\u7ffb\u9875\u5e76\u6293\u53d6\u6570\u636e\u3002<\/p>\n
\u7ffb\u9875\u8fc7\u7a0b\u4e2d\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong>
\u5728\u7ffb\u9875\u65f6\uff0c\u8bb8\u591a\u7f51\u7ad9\u4f1a\u91c7\u53d6\u53cd\u722c\u866b\u63aa\u65bd\u3002\u4e3a\u4e86\u907f\u514d\u88ab\u5c01\u7981\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u968f\u673a\u7528\u6237\u4ee3\u7406\u3001\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\u3001\u4f7f\u7528\u4ee3\u7406IP\u7b49\u65b9\u6cd5\u3002\u6b64\u5916\uff0c\u5c3d\u91cf\u6a21\u62df\u6b63\u5e38\u7528\u6237\u7684\u6d4f\u89c8\u884c\u4e3a\u4e5f\u662f\u6709\u6548\u7684\u7b56\u7565\uff0c\u6bd4\u5982\u968f\u673a\u70b9\u51fb\u3001\u6eda\u52a8\u9875\u9762\u7b49\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u901a\u8fc7\u94fe\u63a5\u7ffb\u9875\u7684\u65b9\u6cd5\u6709\u5f88\u591a\uff0c\u4e3b\u8981\u5305\u62ec\uff1a\u4f7f\u7528Requests\u5e93\u8bf7\u6c42\u9875\u9762\u3001BeautifulSoup\u89e3\u6790 […]","protected":false},"author":3,"featured_media":1153572,"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\/1153569"}],"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=1153569"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1153569\/revisions"}],"predecessor-version":[{"id":1153573,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1153569\/revisions\/1153573"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1153572"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1153569"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1153569"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1153569"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}