{"id":974664,"date":"2024-12-27T06:06:57","date_gmt":"2024-12-26T22:06:57","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/974664.html"},"modified":"2024-12-27T06:06:59","modified_gmt":"2024-12-26T22:06:59","slug":"python%e5%a6%82%e4%bd%95%e6%8a%93%e5%8f%96%e5%a4%a9%e7%9c%bc%e6%9f%a5","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/974664.html","title":{"rendered":"python\u5982\u4f55\u6293\u53d6\u5929\u773c\u67e5"},"content":{"rendered":"

\"python\u5982\u4f55\u6293\u53d6\u5929\u773c\u67e5\"<\/p>\n

\u6293\u53d6\u5929\u773c\u67e5\u7b49\u7f51\u7ad9\u7684\u6570\u636e\u9700\u8981\u4f7f\u7528\u5408\u9002\u7684\u7f51\u7edc\u722c\u866b\u5e93\u3001\u5904\u7406\u53cd\u722c\u673a\u5236\u3001\u9075\u5faa\u6cd5\u5f8b\u6cd5\u89c4<\/strong>\u3002\u5728\u5904\u7406\u53cd\u722c\u673a\u5236\u65b9\u9762\uff0c\u901a\u5e38\u9700\u8981\u4f2a\u88c5\u8bf7\u6c42\u3001\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u9891\u7387\u4ee5\u53ca\u4f7f\u7528\u4ee3\u7406IP\u6765\u89c4\u907f\u8bbf\u95ee\u9650\u5236\u3002\u5bf9\u4e8e\u6570\u636e\u7684\u89e3\u6790\uff0c\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u6216lxml\u7b49\u5e93\u89e3\u6790HTML\u6587\u6863\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u6293\u53d6\u6b64\u7c7b\u7f51\u7ad9\u7684\u6570\u636e\u5fc5\u987b\u4e25\u683c\u9075\u5faa\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u7684robots\u534f\u8bae\uff0c\u4ee5\u907f\u514d\u6cd5\u5f8b\u95ee\u9898\u6216\u8d26\u53f7\u5c01\u7981\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u5b9e\u73b0\u8fd9\u4e00\u8fc7\u7a0b\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528\u5408\u9002\u7684\u7f51\u7edc\u722c\u866b\u5e93<\/h2>\n<\/p>\n

Python\u6709\u8bb8\u591a\u4f18\u79c0\u7684\u7f51\u7edc\u722c\u866b\u5e93\uff0c\u5176\u4e2d\u6700\u5e38\u7528\u7684\u662fRequests\u548cScrapy\u3002<\/p>\n<\/p>\n

1. Requests\u5e93<\/h3>\n<\/p>\n

Requests\u662f\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u5e93\uff0c\u9002\u5408\u7528\u4e8e\u5c0f\u89c4\u6a21\u7684\u722c\u866b\u9879\u76ee\u3002\u4f7f\u7528Requests\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n

import requests<\/p>\n
url = 'https:\/\/www.tianyancha.com\/'<\/p>\n
headers = {<\/p>\n
    'User-Agent': 'Your User Agent'<\/p>\n
}<\/p>\n
response = requests.get(url, headers=headers)<\/p>\n
print(response.text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. Scrapy\u6846\u67b6<\/h3>\n<\/p>\n
Scrapy\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u7528\u4e8e\u5927\u578b\u7684\u722c\u866b\u9879\u76ee\u3002\u5b83\u4e0d\u4ec5\u80fd\u591f\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u8fd8\u80fd\u65b9\u4fbf\u5730\u7ba1\u7406\u722c\u53d6\u6d41\u7a0b\u3001\u89e3\u6790\u6570\u636e\u7b49\u3002<\/p>\n<\/p>\n
import scrapy<\/p>\n
class TianyanchaSpider(scrapy.Spider):<\/p>\n
    name = 'tianyancha'<\/p>\n
    start_urls = ['https:\/\/www.tianyancha.com\/']<\/p>\n
    def parse(self, response):<\/p>\n
        self.log(response.text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u5904\u7406\u53cd\u722c\u673a\u5236<\/h2>\n<\/p>\n
1. \u4f2a\u88c5\u8bf7\u6c42<\/h3>\n<\/p>\n
\u4f2a\u88c5\u8bf7\u6c42\u662f\u5904\u7406\u53cd\u722c\u673a\u5236\u7684\u5e38\u89c1\u624b\u6bb5\u4e4b\u4e00\uff0c\u901a\u5e38\u9700\u8981\u8bbe\u7f6e\u8bf7\u6c42\u5934\u90e8\u4fe1\u606f\uff0c\u5c24\u5176\u662fUser-Agent\u3002<\/p>\n<\/p>\n
headers = {<\/p>\n
    'User-Agent': 'Your User Agent',<\/p>\n
    'Accept-Language': 'en-US,en;q=0.9',<\/p>\n
}<\/p>\n
response = requests.get(url, headers=headers)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u9891\u7387<\/h3>\n<\/p>\n
\u4e3a\u4e86\u907f\u514d\u89e6\u53d1\u53cd\u722c\u673a\u5236\uff0c\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u9891\u7387\u662f\u5fc5\u8981\u7684\u3002\u53ef\u4ee5\u901a\u8fc7time.sleep()<\/code>\u51fd\u6570\u6765\u63a7\u5236\u8bf7\u6c42\u7684\u95f4\u9694\u65f6\u95f4\u3002<\/p>\n<\/p>\n
import time<\/p>\n
for i in range(10):<\/p>\n
    response = requests.get(url, headers=headers)<\/p>\n
    print(response.status_code)<\/p>\n
    time.sleep(5)  # \u7b49\u5f855\u79d2<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u4f7f\u7528\u4ee3\u7406IP<\/h3>\n<\/p>\n
\u5728\u8bbf\u95ee\u91cf\u8f83\u5927\u65f6\uff0c\u4f7f\u7528\u4ee3\u7406IP\u662f\u6709\u6548\u7684\u624b\u6bb5\u3002\u53ef\u4ee5\u901a\u8fc7\u7b2c\u4e09\u65b9\u4ee3\u7406\u670d\u52a1\u83b7\u53d6\u4ee3\u7406IP\u5217\u8868\uff0c\u5e76\u5728\u8bf7\u6c42\u65f6\u968f\u673a\u9009\u62e9\u4e00\u4e2a\u4ee3\u7406IP\u3002<\/p>\n<\/p>\n
proxies = {<\/p>\n
    'http': 'http:\/\/yourproxy:port',<\/p>\n
    'https': 'http:\/\/yourproxy:port',<\/p>\n
}<\/p>\n
response = requests.get(url, headers=headers, proxies=proxies)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u89e3\u6790\u6570\u636e<\/h2>\n<\/p>\n
1. \u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/h3>\n<\/p>\n
BeautifulSoup\u662f\u4e00\u4e2a\u5e38\u7528\u7684HTML\u89e3\u6790\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u4eceHTML\u6587\u6863\u4e2d\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
soup = BeautifulSoup(response.text, 'html.parser')<\/p>\n
titles = soup.find_all('h1')<\/p>\n
for title in titles:<\/p>\n
    print(title.get_text())<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528lxml\u89e3\u6790HTML<\/h3>\n<\/p>\n
lxml\u662f\u53e6\u4e00\u4e2a\u6d41\u884c\u7684\u89e3\u6790\u5e93\uff0c\u652f\u6301XPath\u8bed\u6cd5\uff0c\u53ef\u4ee5\u66f4\u7cbe\u786e\u5730\u5b9a\u4f4d\u6570\u636e\u3002<\/p>\n<\/p>\n
from lxml import etree<\/p>\n
tree = etree.HTML(response.text)<\/p>\n
titles = tree.xpath('\/\/h1\/text()')<\/p>\n
for title in titles:<\/p>\n
    print(title)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u9075\u5faa\u6cd5\u5f8b\u6cd5\u89c4<\/h2>\n<\/p>\n
1. \u9075\u5faarobots\u534f\u8bae<\/h3>\n<\/p>\n
\u5728\u6293\u53d6\u4efb\u4f55\u7f51\u7ad9\u4e4b\u524d\uff0c\u68c0\u67e5\u8be5\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\uff0c\u4ee5\u786e\u4fdd\u9075\u5faa\u5176\u722c\u866b\u534f\u8bae\u3002<\/p>\n<\/p>\n
User-agent: *<\/p>\n
Disallow: \/path<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u6cd5\u5f8b\u5408\u89c4<\/h3>\n<\/p>\n
\u6293\u53d6\u6570\u636e\u65f6\u5fc5\u987b\u9075\u5faa\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\uff0c\u786e\u4fdd\u6570\u636e\u7684\u4f7f\u7528\u7b26\u5408\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u548c\u76f8\u5173\u6cd5\u5f8b\u8981\u6c42\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u5b9e\u6218\u793a\u4f8b<\/h2>\n<\/p>\n
1. \u83b7\u53d6\u516c\u53f8\u4fe1\u606f<\/h3>\n<\/p>\n
\u5047\u8bbe\u6211\u4eec\u9700\u8981\u83b7\u53d6\u5929\u773c\u67e5\u4e0a\u7684\u516c\u53f8\u4fe1\u606f\uff0c\u9996\u5148\u8981\u786e\u5b9a\u76ee\u6807\u9875\u9762\u7684URL\u7ed3\u6784\uff0c\u7136\u540e\u6784\u5efa\u722c\u866b\u7a0b\u5e8f\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
from lxml import etree<\/p>\n
def fetch_company_info(company_name):<\/p>\n
    url = f'https:\/\/www.tianyancha.com\/search?key={company_name}'<\/p>\n
    headers = {<\/p>\n
        'User-Agent': 'Your User Agent'<\/p>\n
    }<\/p>\n
    response = requests.get(url, headers=headers)<\/p>\n
    tree = etree.HTML(response.text)<\/p>\n
    company_info = tree.xpath('\/\/div[@class="company-text"]\/text()')<\/p>\n
    return company_info<\/p>\n
company_name = "Your Company Name"<\/p>\n
info = fetch_company_info(company_name)<\/p>\n
print(info)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u89e3\u6790\u516c\u53f8\u8be6\u60c5<\/h3>\n<\/p>\n
\u5728\u83b7\u53d6\u516c\u53f8\u5217\u8868\u540e\uff0c\u8fd8\u53ef\u4ee5\u8fdb\u4e00\u6b65\u89e3\u6790\u516c\u53f8\u8be6\u60c5\u9875\u9762\uff0c\u4ee5\u83b7\u53d6\u66f4\u8be6\u7ec6\u7684\u4fe1\u606f\u3002<\/p>\n<\/p>\n
def fetch_company_detAI<\/a>ls(company_url):<\/p>\n
    headers = {<\/p>\n
        'User-Agent': 'Your User Agent'<\/p>\n
    }<\/p>\n
    response = requests.get(company_url, headers=headers)<\/p>\n
    tree = etree.HTML(response.text)<\/p>\n
    details = tree.xpath('\/\/div[@class="content"]\/text()')<\/p>\n
    return details<\/p>\n
company_url = "Your Company URL"<\/p>\n
details = fetch_company_details(company_url)<\/p>\n
print(details)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u6570\u636e\u5b58\u50a8<\/h3>\n<\/p>\n
\u6700\u7ec8\u83b7\u53d6\u7684\u6570\u636e\u53ef\u4ee5\u5b58\u50a8\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u5206\u6790\u3002<\/p>\n<\/p>\n
import csv<\/p>\n
def save_to_csv(data, filename):<\/p>\n
    with open(filename, 'w', newline='') as csvfile:<\/p>\n
        writer = csv.writer(csvfile)<\/p>\n
        writer.writerow(['Company Name', 'Info'])<\/p>\n
        for item in data:<\/p>\n
            writer.writerow(item)<\/p>\n
data = [(company_name, info)]<\/p>\n
save_to_csv(data, 'companies.csv')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u603b\u7ed3<\/h2>\n<\/p>\n
\u6293\u53d6\u5929\u773c\u67e5\u7b49\u7f51\u7ad9\u7684\u6570\u636e\u9700\u8981\u4f7f\u7528\u5408\u9002\u7684\u722c\u866b\u5de5\u5177\u3001\u5904\u7406\u53cd\u722c\u673a\u5236\u3001\u89e3\u6790\u6570\u636e\u5e76\u5b58\u50a8\uff0c\u540c\u65f6\u5fc5\u987b\u9075\u5faa\u6cd5\u5f8b\u6cd5\u89c4\u3002\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u6211\u4eec\u4e86\u89e3\u4e86\u5982\u4f55\u4f7f\u7528Requests\u548cScrapy\u5e93\u5b9e\u73b0\u7f51\u7edc\u722c\u866b\uff0c\u5982\u4f55\u5904\u7406\u53cd\u722c\u673a\u5236\uff0c\u4ee5\u53ca\u5982\u4f55\u89e3\u6790\u548c\u5b58\u50a8\u6570\u636e\u3002\u5e0c\u671b\u672c\u6587\u80fd\u4e3a\u60a8\u5b9e\u73b0\u6570\u636e\u6293\u53d6\u63d0\u4f9b\u6709\u4ef7\u503c\u7684\u53c2\u8003\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u6293\u53d6\u5929\u773c\u67e5\u7684\u6570\u636e\uff1f<\/strong>
\u4f7f\u7528Python\u6293\u53d6\u5929\u773c\u67e5\u7684\u6570\u636e\u901a\u5e38\u6d89\u53ca\u5230\u7f51\u9875\u8bf7\u6c42\u548c\u6570\u636e\u89e3\u6790\u3002\u53ef\u4ee5\u4f7f\u7528requests<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u63a5\u7740\u5229\u7528BeautifulSoup<\/code>\u5e93\u89e3\u6790HTML\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684robots.txt\u534f\u8bae\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u5bfc\u81f4IP\u88ab\u5c01\u3002<\/p>\n
\u6293\u53d6\u5929\u773c\u67e5\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u4f26\u7406\u95ee\u9898\uff1f<\/strong>
\u5728\u6293\u53d6\u5929\u773c\u67e5\u6570\u636e\u65f6\uff0c\u7528\u6237\u5e94\u4e86\u89e3\u76f8\u5173\u7684\u6cd5\u5f8b\u6cd5\u89c4\uff0c\u786e\u4fdd\u4e0d\u4fb5\u72af\u4ed6\u4eba\u7684\u77e5\u8bc6\u4ea7\u6743\u3002\u90e8\u5206\u6570\u636e\u53ef\u80fd\u53d7\u5230\u7248\u6743\u4fdd\u62a4\uff0c\u4f7f\u7528\u65f6\u5e94\u83b7\u5f97\u76f8\u5e94\u7684\u6388\u6743\u3002\u6b64\u5916\uff0c\u9891\u7e41\u7684\u8bf7\u6c42\u53ef\u80fd\u5bf9\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\uff0c\u56e0\u6b64\u8981\u5408\u7406\u5b89\u6392\u8bf7\u6c42\u9891\u7387\uff0c\u907f\u514d\u5bf9\u670d\u52a1\u9020\u6210\u5f71\u54cd\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u5929\u773c\u67e5\u8fd4\u56de\u7684\u6570\u636e\u683c\u5f0f\uff1f<\/strong>
\u5929\u773c\u67e5\u8fd4\u56de\u7684\u6570\u636e\u901a\u5e38\u4e3aHTML\u683c\u5f0f\uff0c\u6293\u53d6\u540e\u9700\u8981\u901a\u8fc7\u89e3\u6790\u5de5\u5177\u63d0\u53d6\u7279\u5b9a\u4fe1\u606f\u3002\u4f7f\u7528BeautifulSoup<\/code>\u53ef\u4ee5\u65b9\u4fbf\u5730\u67e5\u627e\u7279\u5b9a\u6807\u7b7e\u548c\u7c7b\u540d\uff0c\u63d0\u53d6\u516c\u53f8\u540d\u79f0\u3001\u6ce8\u518c\u4fe1\u606f\u3001\u80a1\u4e1c\u4fe1\u606f\u7b49\u3002\u5982\u679c\u9700\u8981\u5c06\u6570\u636e\u5b58\u50a8\uff0c\u53ef\u8003\u8651\u5c06\u5176\u8f6c\u6362\u4e3aJSON\u683c\u5f0f\u6216\u5b58\u50a8\u5230\u6570\u636e\u5e93\u4e2d\uff0c\u4fbf\u4e8e\u540e\u7eed\u7684\u6570\u636e\u5206\u6790\u548c\u4f7f\u7528\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u6293\u53d6\u5929\u773c\u67e5\u7b49\u7f51\u7ad9\u7684\u6570\u636e\u9700\u8981\u4f7f\u7528\u5408\u9002\u7684\u7f51\u7edc\u722c\u866b\u5e93\u3001\u5904\u7406\u53cd\u722c\u673a\u5236\u3001\u9075\u5faa\u6cd5\u5f8b\u6cd5\u89c4\u3002\u5728\u5904\u7406\u53cd\u722c\u673a\u5236\u65b9\u9762\uff0c\u901a\u5e38\u9700\u8981\u4f2a\u88c5\u8bf7 […]","protected":false},"author":3,"featured_media":974678,"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\/974664"}],"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=974664"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/974664\/revisions"}],"predecessor-version":[{"id":974681,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/974664\/revisions\/974681"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/974678"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=974664"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=974664"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=974664"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}