pip install pandas<\/p>\n<\/code><\/pre>\n<\/p>\n
\u7136\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528pandas.read_html()\u65b9\u6cd5\u6765\u89e3\u6790\u7f51\u9875\u4e2d\u7684\u8868\u683c\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\ntables = pd.read_html(html_content)<\/p>\n
for table in tables:<\/p>\n
print(table.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u63d0\u53d6\u4e86\u7f51\u9875\u4e2d\u7684\u6240\u6709\u8868\u683c\uff0c\u5e76\u6253\u5370\u4e86\u6bcf\u4e2a\u8868\u683c\u7684\u524d\u51e0\u884c\u3002<\/p>\n<\/p>\n
\n- \u89e3\u6790JSON\u6570\u636e
\u5982\u679c\u7f51\u9875\u8fd4\u56de\u7684\u662fJSON\u6570\u636e\uff0c\u53ef\u4ee5\u76f4\u63a5\u4f7f\u7528requests\u5e93\u7684.json()\u65b9\u6cd5\u89e3\u6790\uff1a<\/li>\n<\/ol>\njson_data = response.json()<\/p>\nprint(json_data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u6837\u53ef\u4ee5\u8f7b\u677e\u89e3\u6790\u548c\u5904\u7406\u7f51\u9875\u4e2d\u7684JSON\u6570\u636e\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u5904\u7406\u7f51\u9875\u4e2d\u7684\u56fe\u50cf\u548c\u6587\u4ef6
\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u53ef\u80fd\u9700\u8981\u4e0b\u8f7d\u7f51\u9875\u4e2d\u7684\u56fe\u50cf\u6216\u5176\u4ed6\u6587\u4ef6\u3002<\/p>\n<\/p>\n
\n- \u4e0b\u8f7d\u56fe\u50cf
\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u56fe\u50cf\u6587\u4ef6\uff1a<\/li>\n<\/ol>\nimage_url = 'http:\/\/example.com\/image.png'<\/p>\nimage_response = requests.get(image_url)<\/p>\n
with open('image.png', 'wb') as file:<\/p>\n
file.write(image_response.content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4e0b\u8f7d\u4e86\u4e00\u4e2a\u56fe\u50cf\u6587\u4ef6\uff0c\u5e76\u5c06\u5176\u4fdd\u5b58\u5230\u672c\u5730\u3002<\/p>\n<\/p>\n
\n- \u5904\u7406\u5176\u4ed6\u6587\u4ef6
\u7c7b\u4f3c\u4e8e\u4e0b\u8f7d\u56fe\u50cf\uff0c\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u5176\u4ed6\u7c7b\u578b\u7684\u6587\u4ef6\uff0c\u4f8b\u5982PDF\u3001CSV\u7b49\uff1a<\/li>\n<\/ol>\nfile_url = 'http:\/\/example.com\/file.pdf'<\/p>\nfile_response = requests.get(file_url)<\/p>\n
with open('file.pdf', 'wb') as file:<\/p>\n
file.write(file_response.content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4e0b\u8f7d\u4e86\u4e00\u4e2aPDF\u6587\u4ef6\uff0c\u5e76\u5c06\u5176\u4fdd\u5b58\u5230\u672c\u5730\u3002<\/p>\n<\/p>\n
\u516d\u3001\u5904\u7406\u7f51\u9875\u4e2d\u7684Cookies\u548c\u4f1a\u8bdd
\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u7f51\u9875\u53ef\u80fd\u9700\u8981\u5904\u7406Cookies\u6216\u4fdd\u6301\u4f1a\u8bdd\u3002<\/p>\n<\/p>\n
\n- \u4f7f\u7528requests.Session()
requests\u5e93\u63d0\u4f9b\u4e86Session\u5bf9\u8c61\uff0c\u53ef\u4ee5\u7528\u4e8e\u7ba1\u7406\u4f1a\u8bdd\u548cCookies\uff1a<\/li>\n<\/ol>\nsession = requests.Session()<\/p>\nresponse = session.get('http:\/\/example.com')<\/p>\n
print(response.cookies)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4f7f\u7528Session\u5bf9\u8c61\uff0c\u53ef\u4ee5\u5728\u591a\u4e2a\u8bf7\u6c42\u4e4b\u95f4\u5171\u4eabCookies\u548c\u5176\u4ed6\u4f1a\u8bdd\u6570\u636e\u3002<\/p>\n<\/p>\n
\n- \u81ea\u5b9a\u4e49\u8bf7\u6c42\u5934
\u53ef\u4ee5\u901a\u8fc7\u81ea\u5b9a\u4e49\u8bf7\u6c42\u5934\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u4ece\u800c\u63d0\u9ad8\u6293\u53d6\u6210\u529f\u7387\uff1a<\/li>\n<\/ol>\nheaders = {<\/p>\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'<\/p>\n
}<\/p>\n
response = requests.get('http:\/\/example.com', headers=headers)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u81ea\u5b9a\u4e49\u4e86User-Agent\u8bf7\u6c42\u5934\uff0c\u4ee5\u6a21\u62df\u771f\u5b9e\u7684\u6d4f\u89c8\u5668\u8bf7\u6c42\u3002<\/p>\n<\/p>\n
\u4e03\u3001\u5904\u7406\u7f51\u9875\u4e2d\u7684\u9519\u8bef\u548c\u5f02\u5e38
\u5728\u6293\u53d6\u7f51\u9875\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u9519\u8bef\u548c\u5f02\u5e38\uff0c\u9700\u8981\u8fdb\u884c\u5904\u7406\u3002<\/p>\n<\/p>\n
\n- \u5904\u7406HTTP\u9519\u8bef
\u53ef\u4ee5\u901a\u8fc7\u68c0\u67e5\u54cd\u5e94\u7684\u72b6\u6001\u7801\u6765\u5904\u7406HTTP\u9519\u8bef\uff1a<\/li>\n<\/ol>\nif response.status_code == 200:<\/p>\n print('Request successful')<\/p>\n
else:<\/p>\n
print('Request failed with status code:', response.status_code)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u68c0\u67e5\u72b6\u6001\u7801\uff0c\u53ef\u4ee5\u5224\u65ad\u8bf7\u6c42\u662f\u5426\u6210\u529f\uff0c\u5e76\u8fdb\u884c\u76f8\u5e94\u5904\u7406\u3002<\/p>\n<\/p>\n
\n- \u6355\u83b7\u5f02\u5e38
\u4f7f\u7528try-except\u8bed\u53e5\u53ef\u4ee5\u6355\u83b7\u548c\u5904\u7406\u5f02\u5e38\uff1a<\/li>\n<\/ol>\ntry:<\/p>\n response = requests.get('http:\/\/example.com')<\/p>\n
response.raise_for_status() # \u5982\u679c\u8bf7\u6c42\u5931\u8d25\uff0c\u4f1a\u5f15\u53d1HTTPError\u5f02\u5e38<\/p>\n
except requests.exceptions.HTTPError as e:<\/p>\n
print('HTTP error occurred:', e)<\/p>\n
except requests.exceptions.RequestException as e:<\/p>\n
print('Request exception occurred:', e)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u6355\u83b7\u4e86HTTPError\u548cRequestException\u5f02\u5e38\uff0c\u5e76\u8fdb\u884c\u4e86\u5904\u7406\u3002<\/p>\n<\/p>\n
\u516b\u3001\u4f18\u5316\u548c\u63d0\u9ad8\u6293\u53d6\u6548\u7387
\u5728\u5927\u89c4\u6a21\u6293\u53d6\u65f6\uff0c\u9700\u8981\u8003\u8651\u4f18\u5316\u548c\u63d0\u9ad8\u6293\u53d6\u6548\u7387\u3002<\/p>\n<\/p>\n
\n- \u4f7f\u7528\u591a\u7ebf\u7a0b\u6216\u591a\u8fdb\u7a0b
\u53ef\u4ee5\u4f7f\u7528Python\u7684\u591a\u7ebf\u7a0b\u6216\u591a\u8fdb\u7a0b\u5e93\u6765\u63d0\u9ad8\u6293\u53d6\u6548\u7387\uff1a<\/li>\n<\/ol>\nfrom concurrent.futures import ThreadPoolExecutor<\/p>\ndef fetch_url(url):<\/p>\n
response = requests.get(url)<\/p>\n
return response.text<\/p>\n
urls = ['http:\/\/example.com\/page1', 'http:\/\/example.com\/page2', 'http:\/\/example.com\/page3']<\/p>\n
with ThreadPoolExecutor(max_workers=5) as executor:<\/p>\n
results = executor.map(fetch_url, urls)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528ThreadPoolExecutor\u5e76\u53d1\u6293\u53d6\u591a\u4e2aURL\u3002<\/p>\n<\/p>\n
\n- \u4f7f\u7528\u5f02\u6b65IO
\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5f02\u6b65IO\u5e93\u6765\u63d0\u9ad8\u6293\u53d6\u6548\u7387\uff1a<\/li>\n<\/ol>\nimport aiohttp<\/p>\nimport asyncio<\/p>\n
async def fetch_url(session, url):<\/p>\n
async with session.get(url) as response:<\/p>\n
return await response.text()<\/p>\n
async def main():<\/p>\n
urls = ['http:\/\/example.com\/page1', 'http:\/\/example.com\/page2', 'http:\/\/example.com\/page3']<\/p>\n
async with aiohttp.ClientSession() as session:<\/p>\n
tasks = [fetch_url(session, url) for url in urls]<\/p>\n
results = await asyncio.gather(*tasks)<\/p>\n
asyncio.run(main())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528aiohttp\u548casyncio\u5e93\u5b9e\u73b0\u4e86\u5f02\u6b65\u6293\u53d6\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n \u5982\u4f55\u4f7f\u7528Python\u8bfb\u53d6\u7f51\u9875\u5185\u5bb9\u7684\u57fa\u672c\u65b9\u6cd5\u662f\u4ec0\u4e48\uff1f<\/strong>
Python\u4e2d\u8bfb\u53d6\u7f51\u9875\u5185\u5bb9\u7684\u57fa\u672c\u65b9\u6cd5\u901a\u5e38\u5305\u62ec\u4f7f\u7528requests<\/code>\u5e93\u548cBeautifulSoup<\/code>\u5e93\u3002requests<\/code>\u5e93\u53ef\u4ee5\u7528\u6765\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u800cBeautifulSoup<\/code>\u5219\u53ef\u4ee5\u5e2e\u52a9\u89e3\u6790\u8fd9\u4e9bHTML\u5185\u5bb9\uff0c\u4ee5\u4fbf\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002\u9996\u5148\uff0c\u786e\u4fdd\u5b89\u88c5\u8fd9\u4e24\u4e2a\u5e93\uff0c\u7136\u540e\u53ef\u4ee5\u901a\u8fc7\u7b80\u5355\u7684\u4ee3\u7801\u793a\u4f8b\u6765\u5b9e\u73b0\u7f51\u9875\u5185\u5bb9\u7684\u8bfb\u53d6\u548c\u89e3\u6790\u3002<\/p>\n\u4f7f\u7528Python\u8bfb\u53d6\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u5982\u4f55\u5904\u7406\u7f51\u9875\u4e2d\u7684\u52a8\u6001\u6570\u636e\uff1f<\/strong>
\u5904\u7406\u52a8\u6001\u6570\u636e\u65f6\uff0c\u5e38\u89c4\u7684requests<\/code>\u5e93\u53ef\u80fd\u65e0\u6cd5\u76f4\u63a5\u83b7\u53d6\u6240\u9700\u5185\u5bb9\uff0c\u56e0\u4e3a\u8fd9\u4e9b\u6570\u636e\u53ef\u80fd\u662f\u901a\u8fc7JavaScript\u52a0\u8f7d\u7684\u3002\u6b64\u65f6\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528Selenium<\/code>\u5e93\uff0c\u5b83\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u80fd\u591f\u6267\u884cJavaScript\u5e76\u83b7\u53d6\u5b8c\u6574\u6e32\u67d3\u540e\u7684\u7f51\u9875\u5185\u5bb9\u3002\u8fd9\u79cd\u65b9\u6cd5\u9002\u7528\u4e8e\u90a3\u4e9b\u9700\u8981\u7528\u6237\u4ea4\u4e92\u6216\u5728\u9875\u9762\u52a0\u8f7d\u540e\u624d\u663e\u793a\u7684\u6570\u636e\u3002<\/p>\n\u5728\u8bfb\u53d6\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong>
\u8bb8\u591a\u7f51\u7ad9\u4f1a\u5b9e\u65bd\u53cd\u722c\u866b\u673a\u5236\uff0c\u4ee5\u9632\u6b62\u81ea\u52a8\u5316\u811a\u672c\u6293\u53d6\u6570\u636e\u3002\u4e3a\u4e86\u6709\u6548\u8bfb\u53d6\u8fd9\u4e9b\u7f51\u9875\u5185\u5bb9\uff0c\u53ef\u4ee5\u5c1d\u8bd5\u66f4\u6539\u8bf7\u6c42\u5934\uff0c\u4f2a\u88c5\u6210\u6b63\u5e38\u7684\u6d4f\u89c8\u5668\u8bf7\u6c42\u3002\u6b64\u5916\uff0c\u8bbe\u7f6e\u8bf7\u6c42\u7684\u95f4\u9694\u65f6\u95f4\u3001\u4f7f\u7528\u4ee3\u7406IP\u548c\u968f\u673a\u5316\u7528\u6237\u4ee3\u7406\u4e5f\u662f\u6709\u6548\u7684\u7b56\u7565\u3002\u540c\u65f6\uff0c\u9075\u5faa\u7f51\u7ad9\u7684robots.txt<\/code>\u534f\u8bae\uff0c\u786e\u4fdd\u4e0d\u8fdd\u53cd\u76f8\u5173\u6cd5\u5f8b\u548c\u7f51\u7ad9\u89c4\u5b9a\uff0c\u4fdd\u6301\u826f\u597d\u7684\u722c\u866b\u884c\u4e3a\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5f00\u5934\u6bb5\u843d\uff1aPython\u8bfb\u53d6\u7f51\u9875\u5185\u5bb9\u7684\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528Beautiful […]","protected":false},"author":3,"featured_media":960642,"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\/960635"}],"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=960635"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/960635\/revisions"}],"predecessor-version":[{"id":960646,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/960635\/revisions\/960646"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/960642"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=960635"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=960635"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=960635"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"python\u5982\u4f55\u8bfb\u53d6\u7f51\u9875\u5185\u5bb9\"](\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25103056\/d8b6e303-acb8-40ee-a4cb-89474710395d.webp\")
<\/p>\n