{"id":945297,"date":"2024-12-26T23:24:27","date_gmt":"2024-12-26T15:24:27","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/945297.html"},"modified":"2024-12-26T23:24:29","modified_gmt":"2024-12-26T15:24:29","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e6%96%87%e4%bb%b6","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/945297.html","title":{"rendered":"python\u5982\u4f55\u722c\u6587\u4ef6"},"content":{"rendered":"

\"python\u5982\u4f55\u722c\u6587\u4ef6\"<\/p>\n

Python\u722c\u53d6\u6587\u4ef6\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u4e3b\u8981\u5305\u62ec\u4f7f\u7528HTTP\u8bf7\u6c42\u5e93\u5982requests\u3001\u7ed3\u5408BeautifulSoup\u89e3\u6790HTML\u9875\u9762\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u9ad8\u7ea7\u722c\u866b\u5f00\u53d1\u3002\u8fd9\u4e9b\u65b9\u6cd5\u5404\u6709\u4f18\u52a3\uff0crequests\u9002\u5408\u7b80\u5355\u7684\u4e0b\u8f7d\u4efb\u52a1\uff0cBeautifulSoup\u9002\u5408\u89e3\u6790HTML\u7ed3\u6784\u8f83\u4e3a\u7b80\u5355\u7684\u7f51\u9875\uff0cScrapy\u5219\u9002\u5408\u9700\u8981\u5904\u7406\u5927\u91cf\u6570\u636e\u548c\u590d\u6742\u903b\u8f91\u7684\u4efb\u52a1\u3002<\/strong>\u5728\u8fd9\u4e9b\u65b9\u6cd5\u4e2d\uff0crequests\u5e93\u662f\u6700\u5e38\u7528\u4e14\u6613\u4e8e\u4e0a\u624b\u7684\uff0c\u901a\u8fc7\u7b80\u5355\u7684GET\u8bf7\u6c42\u5373\u53ef\u4e0b\u8f7d\u6587\u4ef6\u3002<\/p>\n<\/p>\n

\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u63a2\u8ba8\u6bcf\u79cd\u65b9\u6cd5\u7684\u4f7f\u7528\u573a\u666f\u548c\u6b65\u9aa4\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528REQUESTS\u5e93\u722c\u53d6\u6587\u4ef6<\/h3>\n<\/p>\n

requests\u5e93\u662fPython\u4e2d\u6700\u6d41\u884c\u7684HTTP\u8bf7\u6c42\u5e93\u4e4b\u4e00\uff0c\u56e0\u5176\u7b80\u6d01\u7684API\u8bbe\u8ba1\u800c\u5907\u53d7\u6b22\u8fce\u3002\u4f7f\u7528requests\u5e93\u53ef\u4ee5\u8f7b\u677e\u5730\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u548c\u4e0b\u8f7d\u6587\u4ef6\u3002<\/p>\n<\/p>\n

1. \u57fa\u672c\u4f7f\u7528\u65b9\u6cd5<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5requests\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7pip\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install requests<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u7136\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u4ee3\u7801\u4e0b\u8f7d\u6587\u4ef6\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'http:\/\/example.com\/file.txt'<\/p>\n
response = requests.get(url)<\/p>\n
with open('file.txt', 'wb') as file:<\/p>\n
    file.write(response.content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528requests.get()<\/code>\u65b9\u6cd5\u53d1\u9001GET\u8bf7\u6c42\uff0c\u83b7\u53d6\u6587\u4ef6\u5185\u5bb9\u3002response.content<\/code>\u8fd4\u56de\u7684\u662f\u6587\u4ef6\u7684\u4e8c\u8fdb\u5236\u5185\u5bb9\uff0c\u6211\u4eec\u5c06\u5176\u5199\u5165\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n
2. \u5904\u7406\u5927\u6587\u4ef6\u4e0b\u8f7d<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u5927\u6587\u4ef6\u4e0b\u8f7d\uff0c\u5efa\u8bae\u4f7f\u7528\u6d41\u5f0f\u4e0b\u8f7d\uff0c\u4ee5\u907f\u514d\u5360\u7528\u8fc7\u591a\u5185\u5b58\u3002\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6estream=True<\/code>\u6765\u5b9e\u73b0\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'http:\/\/example.com\/largefile.zip'<\/p>\n
response = requests.get(url, stream=True)<\/p>\n
with open('largefile.zip', 'wb') as file:<\/p>\n
    for chunk in response.iter_content(chunk_size=1024):<\/p>\n
        if chunk:<\/p>\n
            file.write(chunk)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u79cd\u65b9\u5f0f\u4f1a\u5c06\u6587\u4ef6\u5206\u5757\u4e0b\u8f7d\uff0c\u6bcf\u6b21\u4e0b\u8f7d\u4e00\u5c0f\u90e8\u5206\uff0c\u76f4\u5230\u6587\u4ef6\u4e0b\u8f7d\u5b8c\u6210\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528BEAUTIFULSOUP\u89e3\u6790HTML\u9875\u9762<\/h3>\n<\/p>\n
BeautifulSoup\u662f\u4e00\u4e2a\u53ef\u4ee5\u4eceHTML\u6216XML\u6587\u4ef6\u4e2d\u63d0\u53d6\u6570\u636e\u7684Python\u5e93\uff0c\u975e\u5e38\u9002\u5408\u5904\u7406\u7ed3\u6784\u8f83\u7b80\u5355\u7684\u7f51\u9875\u3002<\/p>\n<\/p>\n
1. \u57fa\u672c\u4f7f\u7528\u65b9\u6cd5<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u5b89\u88c5BeautifulSoup\u5e93\uff1a<\/p>\n<\/p>\n
pip install beautifulsoup4<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u7136\u540e\uff0c\u7ed3\u5408requests\u5e93\u4f7f\u7528\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
response = requests.get(url)<\/p>\n
soup = BeautifulSoup(response.text, 'html.parser')<\/p>\n
for link in soup.find_all('a'):<\/p>\n
    print(link.get('href'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\uff0c\u5e76\u63d0\u53d6\u6240\u6709\u7684\u94fe\u63a5\u3002<\/p>\n<\/p>\n
2. \u63d0\u53d6\u7279\u5b9a\u7c7b\u578b\u6587\u4ef6\u94fe\u63a5<\/h4>\n<\/p>\n
\u5982\u679c\u6211\u4eec\u9700\u8981\u4e0b\u8f7d\u7279\u5b9a\u7c7b\u578b\u7684\u6587\u4ef6\uff08\u5982PDF\uff09\uff0c\u53ef\u4ee5\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u7b5b\u9009\u94fe\u63a5\uff1a<\/p>\n<\/p>\n
import re<\/p>\n
pdf_links = soup.find_all('a', href=re.compile(r'\\.pdf$'))<\/p>\n
for pdf_link in pdf_links:<\/p>\n
    print(pdf_link.get('href'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u79cd\u65b9\u6cd5\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u5feb\u901f\u5b9a\u4f4d\u5e76\u4e0b\u8f7d\u6211\u4eec\u611f\u5174\u8da3\u7684\u6587\u4ef6\u7c7b\u578b\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528SCRAPY\u6846\u67b6\u8fdb\u884c\u9ad8\u7ea7\u722c\u866b\u5f00\u53d1<\/h3>\n<\/p>\n
Scrapy\u662f\u4e00\u4e2a\u4e3a\u722c\u53d6\u7f51\u7ad9\u6570\u636e\u3001\u63d0\u53d6\u7ed3\u6784\u6027\u6570\u636e\u800c\u7f16\u5199\u7684\u5e94\u7528\u6846\u67b6\u3002\u5b83\u975e\u5e38\u9002\u5408\u9700\u8981\u5904\u7406\u5927\u91cf\u6570\u636e\u548c\u590d\u6742\u903b\u8f91\u7684\u4efb\u52a1\u3002<\/p>\n<\/p>\n
1. \u57fa\u672c\u4f7f\u7528\u65b9\u6cd5<\/h4>\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\uff1a<\/p>\n<\/p>\n
scrapy startproject myproject<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u9879\u76ee\u4e2d\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u722c\u866b\uff1a<\/p>\n<\/p>\n
cd myproject<\/p>\n
scrapy genspider myspider example.com<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u751f\u6210\u7684\u722c\u866b\u6587\u4ef6\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u5b9a\u4e49\u722c\u53d6\u903b\u8f91\uff1a<\/p>\n<\/p>\n
import scrapy<\/p>\n
class MySpider(scrapy.Spider):<\/p>\n
    name = "myspider"<\/p>\n
    start_urls = ['http:\/\/example.com']<\/p>\n
    def parse(self, response):<\/p>\n
        for href in response.css('a::attr(href)').getall():<\/p>\n
            yield response.follow(href, self.parse)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u7ba1\u7406\u5927\u89c4\u6a21\u6570\u636e\u722c\u53d6<\/h4>\n<\/p>\n
Scrapy\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u6570\u636e\u5bfc\u51fa\u529f\u80fd\uff0c\u53ef\u4ee5\u5c06\u722c\u53d6\u7684\u6570\u636e\u4fdd\u5b58\u4e3aJSON\u3001CSV\u7b49\u683c\u5f0f\u3002\u540c\u65f6\uff0cScrapy\u652f\u6301\u4e2d\u95f4\u4ef6\uff0c\u53ef\u4ee5\u5728\u8bf7\u6c42\u548c\u54cd\u5e94\u8fc7\u7a0b\u4e2d\u8fdb\u884c\u6570\u636e\u5904\u7406\u548c\u8fc7\u6ee4\u3002<\/p>\n<\/p>\n
\u56db\u3001\u722c\u53d6\u6587\u4ef6\u65f6\u7684\u6ce8\u610f\u4e8b\u9879<\/h3>\n<\/p>\n
\u5728\u8fdb\u884c\u6587\u4ef6\u722c\u53d6\u65f6\uff0c\u9700\u8981\u6ce8\u610f\u4e00\u4e9b\u6cd5\u5f8b\u548c\u6280\u672f\u4e0a\u7684\u95ee\u9898\uff1a<\/p>\n<\/p>\n
1. \u9075\u5b88\u7f51\u7ad9\u7684robots.txt<\/h4>\n<\/p>\n
\u8bb8\u591a\u7f51\u7ad9\u901a\u8fc7robots.txt\u6587\u4ef6\u6765\u58f0\u660e\u5141\u8bb8\u548c\u7981\u6b62\u722c\u866b\u8bbf\u95ee\u7684\u5185\u5bb9\u3002\u6211\u4eec\u5e94\u8be5\u9075\u5b88\u8fd9\u4e9b\u89c4\u5b9a\uff0c\u907f\u514d\u7ed9\u7f51\u7ad9\u9020\u6210\u4e0d\u5fc5\u8981\u7684\u8d1f\u62c5\u3002<\/p>\n<\/p>\n
2. \u8bbe\u7f6e\u5408\u9002\u7684\u8bf7\u6c42\u95f4\u9694<\/h4>\n<\/p>\n
\u4e3a\u4e86\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u7684\u538b\u529b\uff0c\u6211\u4eec\u5e94\u8be5\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u95f4\u9694\u3002\u53ef\u4ee5\u4f7f\u7528time.sleep()\u51fd\u6570\u6765\u5b9e\u73b0\uff1a<\/p>\n<\/p>\n
import time<\/p>\n
time.sleep(1)  # \u7b49\u5f851\u79d2<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728Scrapy\u4e2d\uff0c\u53ef\u4ee5\u901a\u8fc7\u4e0b\u8f7d\u4e2d\u95f4\u4ef6\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\uff1a<\/p>\n<\/p>\n
DOWNLOAD_DELAY = 1<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h4>\n<\/p>\n
\u8bb8\u591a\u7f51\u7ad9\u4f1a\u4f7f\u7528\u5404\u79cd\u6280\u672f\u624b\u6bb5\u6765\u963b\u6b62\u722c\u866b\uff0c\u5982\u9a8c\u8bc1\u7801\u3001IP\u5c01\u7981\u7b49\u3002\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u4ee3\u7406\u3001\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u7b49\u65b9\u5f0f\u6765\u7ed5\u8fc7\u8fd9\u4e9b\u673a\u5236\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5f3a\u5927\u7684\u5de5\u5177\u6765\u8fdb\u884c\u6587\u4ef6\u722c\u53d6\uff0c\u4ece\u7b80\u5355\u7684requests\u5e93\u5230\u529f\u80fd\u5f3a\u5927\u7684Scrapy\u6846\u67b6\uff0c\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u9ad8\u6548\u5730\u5b8c\u6210\u4efb\u52a1\u3002\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\uff0c\u9075\u5b88\u6cd5\u5f8b\u6cd5\u89c4\u3001\u5c0a\u91cd\u7f51\u7ad9\u7684\u722c\u866b\u534f\u8bae\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002\u5e0c\u671b\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u60a8\u80fd\u591f\u66f4\u597d\u5730\u7406\u89e3\u548c\u4f7f\u7528Python\u8fdb\u884c\u6587\u4ef6\u722c\u53d6\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u4e0b\u8f7d\u6587\u4ef6\uff1f<\/strong>
\u4f7f\u7528Python\u4e0b\u8f7d\u6587\u4ef6\u53ef\u4ee5\u901a\u8fc7\u591a\u79cd\u65b9\u6cd5\u5b9e\u73b0\uff0c\u6700\u5e38\u7528\u7684\u65b9\u6cd5\u662f\u4f7f\u7528requests\u5e93\u3002\u9996\u5148\uff0c\u786e\u4fdd\u5b89\u88c5\u4e86requests\u5e93\uff08\u4f7f\u7528\u547d\u4ee4pip install requests<\/code>\uff09\u3002\u63a5\u4e0b\u6765\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u793a\u4f8b\u6765\u4e0b\u8f7d\u6587\u4ef6\uff1a  <\/p>\n
import requests\n\nurl = 'https:\/\/example.com\/file.zip'  # \u6587\u4ef6\u7684URL\nresponse = requests.get(url)\n\nwith open('file.zip', 'wb') as f:  # \u4fdd\u5b58\u6587\u4ef6\n    f.write(response.content)\n<\/code><\/pre>\n
\u8fd9\u6bb5\u4ee3\u7801\u5c06\u4ece\u6307\u5b9a\u7684URL\u4e0b\u8f7d\u6587\u4ef6\uff0c\u5e76\u5c06\u5176\u4fdd\u5b58\u5728\u5f53\u524d\u76ee\u5f55\u4e0b\u3002<\/p>\n
\u5728\u722c\u866b\u4e2d\u5982\u4f55\u5904\u7406\u6587\u4ef6\u4e0b\u8f7d\u7684\u91cd\u5b9a\u5411\uff1f<\/strong>
\u5728\u8fdb\u884c\u6587\u4ef6\u4e0b\u8f7d\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u91cd\u5b9a\u5411\u7684\u60c5\u51b5\u3002requests\u5e93\u4f1a\u81ea\u52a8\u5904\u7406\u5927\u90e8\u5206\u91cd\u5b9a\u5411\uff0c\u4f46\u5982\u679c\u9700\u8981\u624b\u52a8\u5904\u7406\uff0c\u53ef\u4ee5\u8bbe\u7f6eallow_redirects<\/code>\u53c2\u6570\u3002\u793a\u4f8b\u5982\u4e0b\uff1a  <\/p>\n
response = requests.get(url, allow_redirects=True)\n<\/code><\/pre>\n
\u8fd9\u5c06\u786e\u4fdd\u5728\u4e0b\u8f7d\u6587\u4ef6\u65f6\u80fd\u591f\u8ddf\u968f\u91cd\u5b9a\u5411\uff0c\u987a\u5229\u83b7\u53d6\u76ee\u6807\u6587\u4ef6\u3002<\/p>\n
\u5982\u4f55\u8bbe\u7f6e\u8bf7\u6c42\u5934\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u4e0b\u8f7d\u6587\u4ef6\uff1f<\/strong>
\u67d0\u4e9b\u7f51\u7ad9\u8981\u6c42\u7279\u5b9a\u7684\u8bf7\u6c42\u5934\u624d\u80fd\u6210\u529f\u4e0b\u8f7d\u6587\u4ef6\u3002\u53ef\u4ee5\u901a\u8fc7\u5728requests.get()\u65b9\u6cd5\u4e2d\u6dfb\u52a0headers\u53c2\u6570\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u7684\u8bf7\u6c42\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a  <\/p>\n
headers = {\n    'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3'\n}\nresponse = requests.get(url, headers=headers)\n<\/code><\/pre>\n
\u901a\u8fc7\u8bbe\u7f6eUser-Agent\uff0c\u7f51\u7ad9\u5c06\u628a\u8bf7\u6c42\u89c6\u4e3a\u6765\u81ea\u666e\u901a\u6d4f\u89c8\u5668\uff0c\u4ece\u800c\u51cf\u5c11\u88ab\u62d2\u7edd\u7684\u98ce\u9669\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6\u6587\u4ef6\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u4e3b\u8981\u5305\u62ec\u4f7f\u7528HTTP\u8bf7\u6c42\u5e93\u5982requests\u3001\u7ed3\u5408BeautifulSoup […]","protected":false},"author":3,"featured_media":945304,"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\/945297"}],"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=945297"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/945297\/revisions"}],"predecessor-version":[{"id":945306,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/945297\/revisions\/945306"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/945304"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=945297"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=945297"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=945297"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}