![\"python\u722c\u866b\u5982\u4f55\u722c\u56fe\u7247\"](\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25083835\/57eabb2c-5b8e-45d1-8fe2-2b6cdde63255.webp\")
<\/p>\n<\/p>\n
\u5f00\u5934\u6bb5\u843d: \u4e00\u3001\u7406\u89e3\u722c\u866b\u57fa\u672c\u539f\u7406<\/p>\n<\/p>\n Python\u722c\u866b\u7684\u57fa\u672c\u539f\u7406\u662f\u901a\u8fc7\u6a21\u62df\u6d4f\u89c8\u5668\u7684\u884c\u4e3a\u8bbf\u95ee\u76ee\u6807\u7f51\u7ad9\uff0c\u83b7\u53d6\u9875\u9762\u7684HTML\u6e90\u4ee3\u7801\uff0c\u7136\u540e\u4ece\u4e2d\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002\u5bf9\u4e8e\u56fe\u7247\u722c\u866b\u6765\u8bf4\uff0c\u76ee\u6807\u662f\u4eceHTML\u4e2d\u627e\u5230\u56fe\u7247\u7684URL\uff0c\u5e76\u4e0b\u8f7d\u5230\u672c\u5730\u3002\u722c\u866b\u7684\u6838\u5fc3\u90e8\u5206\u5305\u62ec\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u6587\u6863\u3001\u63d0\u53d6\u6570\u636e\u548c\u5b58\u50a8\u6570\u636e\u3002<\/p>\n<\/p>\n \u5728\u8fdb\u884c\u4efb\u4f55\u722c\u866b\u64cd\u4f5c\u524d\uff0c\u9996\u5148\u9700\u8981\u901a\u8fc7HTTP\u8bf7\u6c42\u8bbf\u95ee\u76ee\u6807\u7f51\u9875\u3002Python\u63d0\u4f9b\u4e86\u591a\u4e2a\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u7684\u5e93\uff0c\u5176\u4e2drequests\u5e93\u662f\u6700\u5e38\u7528\u7684\u3002\u5b83\u80fd\u591f\u7b80\u5316HTTP\u8bf7\u6c42\u7684\u53d1\u9001\u548c\u54cd\u5e94\u7684\u5904\u7406\uff0c\u4f7f\u5f97\u83b7\u53d6\u7f51\u9875\u6e90\u4ee3\u7801\u53d8\u5f97\u975e\u5e38\u7b80\u5355\u3002\u901a\u8fc7requests.get(url)\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u83b7\u53d6\u76ee\u6807\u7f51\u9875\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n \u83b7\u53d6\u5230\u7f51\u9875\u7684HTML\u5185\u5bb9\u540e\uff0c\u63a5\u4e0b\u6765\u9700\u8981\u89e3\u6790HTML\u6587\u6863\uff0c\u4ee5\u4fbf\u4ece\u4e2d\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002BeautifulSoup\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684Python\u5e93\uff0c\u4e13\u95e8\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u3002\u901a\u8fc7\u5b83\uff0c\u6211\u4eec\u53ef\u4ee5\u65b9\u4fbf\u5730\u67e5\u627e\u548c\u64cd\u4f5cHTML\u6587\u6863\u4e2d\u7684\u5404\u4e2a\u5143\u7d20\uff0c\u4f8b\u5982\u6807\u7b7e\u3001\u5c5e\u6027\u548c\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n \u4e8c\u3001\u63d0\u53d6\u56fe\u7247URL<\/p>\n<\/p>\n \u63d0\u53d6\u56fe\u7247URL\u662f\u722c\u53d6\u56fe\u7247\u7684\u5173\u952e\u6b65\u9aa4\u3002\u901a\u5e38\uff0c\u7f51\u9875\u4e2d\u7684\u56fe\u7247\u901a\u8fc7 \u5728\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528find_all\u65b9\u6cd5\u67e5\u627e\u6240\u6709\u7684 soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n img_tags = soup.find_all('img')<\/p>\n <\/code><\/pre>\n<\/p>\n \u627e\u5230 <\/code><\/pre>\n<\/p>\n \u4e09\u3001\u4e0b\u8f7d\u56fe\u7247<\/p>\n<\/p>\n \u5728\u83b7\u53d6\u5230\u56fe\u7247\u7684URL\u540e\uff0c\u4e0b\u4e00\u6b65\u5c31\u662f\u5c06\u56fe\u7247\u4e0b\u8f7d\u5230\u672c\u5730\u3002\u4e3a\u4e86\u786e\u4fdd\u56fe\u7247\u80fd\u591f\u6210\u529f\u4e0b\u8f7d\uff0c\u6211\u4eec\u9700\u8981\u5904\u7406\u5f02\u5e38\u60c5\u51b5\uff0c\u5e76\u8003\u8651\u5982\u4f55\u9ad8\u6548\u5730\u4e0b\u8f7d\u5927\u91cf\u56fe\u7247\u3002<\/p>\n<\/p>\n urllib\u5e93\u63d0\u4f9b\u4e86urlretrieve\u65b9\u6cd5\uff0c\u53ef\u4ee5\u7528\u4e8e\u4e0b\u8f7d\u6587\u4ef6\u3002\u901a\u8fc7\u4f20\u5165\u56fe\u7247\u7684URL\u548c\u672c\u5730\u6587\u4ef6\u8def\u5f84\uff0curlretrieve\u65b9\u6cd5\u4f1a\u81ea\u52a8\u5904\u7406\u7f51\u7edc\u8bf7\u6c42\u548c\u6587\u4ef6\u5199\u5165\u3002<\/p>\n<\/p>\n for img_url in img_urls:<\/p>\n try:<\/p>\n filename = img_url.split('\/')[-1]<\/p>\n urllib.request.urlretrieve(img_url, f'images\/{filename}')<\/p>\n except Exception as e:<\/p>\n print(f"Error downloading {img_url}: {e}")<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u4e0b\u8f7d\u56fe\u7247\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u7f51\u7edc\u8d85\u65f6\u3001URL\u65e0\u6548\u7b49\u5f02\u5e38\u60c5\u51b5\u3002\u4e3a\u4e86\u63d0\u9ad8\u7a0b\u5e8f\u7684\u7a33\u5b9a\u6027\uff0c\u6211\u4eec\u9700\u8981\u5bf9\u8fd9\u4e9b\u5f02\u5e38\u8fdb\u884c\u5904\u7406\uff0c\u4ee5\u514d\u7a0b\u5e8f\u4e2d\u65ad\u3002<\/p>\n<\/p>\n \u5bf9\u4e8e\u5927\u89c4\u6a21\u7684\u56fe\u7247\u4e0b\u8f7d\u4efb\u52a1\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u7ebf\u7a0b\u6280\u672f\u6765\u63d0\u9ad8\u6548\u7387\u3002\u901a\u8fc7concurrent.futures\u6a21\u5757\u7684ThreadPoolExecutor\u7c7b\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5b9e\u73b0\u591a\u7ebf\u7a0b\u4e0b\u8f7d\u3002<\/p>\n<\/p>\n def download_image(img_url):<\/p>\n try:<\/p>\n filename = img_url.split('\/')[-1]<\/p>\n urllib.request.urlretrieve(img_url, f'images\/{filename}')<\/p>\n except Exception as e:<\/p>\n print(f"Error downloading {img_url}: {e}")<\/p>\n with ThreadPoolExecutor(max_workers=10) as executor:<\/p>\n executor.map(download_image, img_urls)<\/p>\n <\/code><\/pre>\n<\/p>\n \u56db\u3001\u7ba1\u7406\u6587\u4ef6\u5b58\u50a8<\/p>\n<\/p>\n \u4e3a\u4e86\u4fbf\u4e8e\u7ba1\u7406\u4e0b\u8f7d\u7684\u56fe\u7247\uff0c\u6211\u4eec\u9700\u8981\u5bf9\u6587\u4ef6\u8fdb\u884c\u5408\u7406\u7684\u5b58\u50a8\u548c\u7ba1\u7406\u3002\u901a\u8fc7os\u5e93\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u521b\u5efa\u76ee\u5f55\u3001\u68c0\u67e5\u6587\u4ef6\u662f\u5426\u5b58\u5728\u7b49\u3002<\/p>\n<\/p>\n \u5728\u4e0b\u8f7d\u56fe\u7247\u524d\uff0c\u9996\u5148\u9700\u8981\u521b\u5efa\u4e00\u4e2a\u76ee\u5f55\u7528\u4e8e\u5b58\u50a8\u56fe\u7247\u3002\u901a\u8fc7os.makedirs\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u4e00\u6b21\u6027\u521b\u5efa\u591a\u7ea7\u76ee\u5f55\u3002<\/p>\n<\/p>\n if not os.path.exists('images'):<\/p>\n os.makedirs('images')<\/p>\n <\/code><\/pre>\n<\/p>\n \u4e3a\u4e86\u907f\u514d\u91cd\u590d\u4e0b\u8f7d\uff0c\u6211\u4eec\u53ef\u4ee5\u5728\u4e0b\u8f7d\u524d\u68c0\u67e5\u6587\u4ef6\u662f\u5426\u5df2\u5b58\u5728\u3002\u5982\u679c\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u53ef\u4ee5\u9009\u62e9\u8df3\u8fc7\u4e0b\u8f7d\u6216\u8986\u76d6\u6587\u4ef6\u3002<\/p>\n<\/p>\n try:<\/p>\n filename = img_url.split('\/')[-1]<\/p>\n filepath = f'images\/{filename}'<\/p>\n if not os.path.exists(filepath):<\/p>\n urllib.request.urlretrieve(img_url, filepath)<\/p>\n except Exception as e:<\/p>\n print(f"Error downloading {img_url}: {e}")<\/p>\n <\/code><\/pre>\n<\/p>\n \u4e94\u3001\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236<\/p>\n<\/p>\n \u8bb8\u591a\u7f51\u7ad9\u4e3a\u4e86\u4fdd\u62a4\u5185\u5bb9\u548c\u670d\u52a1\u5668\u8d44\u6e90\uff0c\u4f1a\u90e8\u7f72\u53cd\u722c\u866b\u673a\u5236\uff0c\u5982IP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u3001\u52a8\u6001\u52a0\u8f7d\u7b49\u3002\u4e3a\u4e86\u6210\u529f\u722c\u53d6\u56fe\u7247\uff0c\u6211\u4eec\u9700\u8981\u4e86\u89e3\u5e76\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\u3002<\/p>\n<\/p>\n \u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\u4fe1\u606f\uff0c\u53ef\u4ee5\u6a21\u62df\u771f\u5b9e\u6d4f\u89c8\u5668\u7684\u8bf7\u6c42\uff0c\u964d\u4f4e\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u7684\u98ce\u9669\u3002\u5e38\u7528\u7684\u8bf7\u6c42\u5934\u5305\u62ecUser-Agent\u3001Referer\u7b49\u3002<\/p>\n<\/p>\n 'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/85.0.4183.121 Safari\/537.36',<\/p>\n 'Referer': 'https:\/\/example.com'<\/p>\n }<\/p>\n response = requests.get(url, headers=headers)<\/p>\n <\/code><\/pre>\n<\/p>\n \u4e3a\u4e86\u907f\u514dIP\u5c01\u7981\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee3\u7406IP\u8fdb\u884c\u8bf7\u6c42\u3002\u901a\u8fc7proxy\u53c2\u6570\uff0crequests\u5e93\u53ef\u4ee5\u8f7b\u677e\u8bbe\u7f6e\u4ee3\u7406\u3002<\/p>\n<\/p>\n 'http': 'http:\/\/10.10.10.10:3128',<\/p>\n 'https': 'https:\/\/10.10.10.10:1080'<\/p>\n }<\/p>\n response = requests.get(url, headers=headers, proxies=proxies)<\/p>\n <\/code><\/pre>\n<\/p>\n \u5bf9\u4e8e\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\u56fe\u7247\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u7b49\u5de5\u5177\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u540e\u7684\u5b8c\u6574HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n driver = webdriver.Chrome()<\/p>\n driver.get(url)<\/p>\n html_content = driver.page_source<\/p>\n driver.quit()<\/p>\n <\/code><\/pre>\n<\/p>\n \u516d\u3001\u5b9e\u6218\u6848\u4f8b\uff1a\u722c\u53d6Unsplash\u56fe\u7247<\/p>\n<\/p>\n \u4e3a\u66f4\u597d\u5730\u7406\u89e3\u4e0a\u8ff0\u8fc7\u7a0b\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4e00\u4e2a\u5b9e\u9645\u6848\u4f8b\u6765\u6f14\u793a\u5982\u4f55\u4f7f\u7528Python\u722c\u866b\u722c\u53d6Unsplash\u7f51\u7ad9\u7684\u56fe\u7247\u3002<\/p>\n<\/p>\n \u9996\u5148\uff0c\u8bbf\u95eeUnsplash\u7f51\u7ad9\uff0c\u5206\u6790\u7f51\u9875\u7ed3\u6784\u3002\u901a\u8fc7\u6d4f\u89c8\u5668\u7684\u5f00\u53d1\u8005\u5de5\u5177\uff0c\u6211\u4eec\u53ef\u4ee5\u53d1\u73b0\u56fe\u7247\u4f7f\u7528 \u57fa\u4e8e\u4e0a\u8ff0\u5206\u6790\uff0c\u6211\u4eec\u53ef\u4ee5\u7f16\u5199\u722c\u866b\u811a\u672c\uff0c\u4eceUnsplash\u7684\u7f51\u9875\u4e2d\u63d0\u53d6\u56fe\u7247URL\u5e76\u4e0b\u8f7d\u3002<\/p>\n<\/p>\n from bs4 import BeautifulSoup<\/p>\n import os<\/p>\n import urllib.request<\/p>\n headers = {<\/p>\n 'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/85.0.4183.121 Safari\/537.36'<\/p>\n }<\/p>\n if not os.path.exists('unsplash_images'):<\/p>\n os.makedirs('unsplash_images')<\/p>\n url = 'https:\/\/unsplash.com\/'<\/p>\n response = requests.get(url, headers=headers)<\/p>\n soup = BeautifulSoup(response.content, 'html.parser')<\/p>\n img_tags = soup.find_all('img')<\/p>\n img_urls = [img['src'] for img in img_tags if 'src' in img.attrs]<\/p>\n for img_url in img_urls:<\/p>\n try:<\/p>\n filename = img_url.split('\/')[-1]<\/p>\n filepath = f'unsplash_images\/{filename}'<\/p>\n if not os.path.exists(filepath):<\/p>\n urllib.request.urlretrieve(img_url, filepath)<\/p>\n except Exception as e:<\/p>\n print(f"Error downloading {img_url}: {e}")<\/p>\n <\/code><\/pre>\n<\/p>\n \u8fd0\u884c\u811a\u672c\u540e\uff0c\u68c0\u67e5unsplash_images\u76ee\u5f55\uff0c\u786e\u8ba4\u56fe\u7247\u5df2\u6210\u529f\u4e0b\u8f7d\u3002<\/p>\n<\/p>\n \u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u770b\u5230\u4f7f\u7528Python\u722c\u866b\u722c\u53d6\u56fe\u7247\u7684\u5168\u8fc7\u7a0b\u3002\u901a\u8fc7\u7ed3\u5408requests\u3001BeautifulSoup\u3001urllib\u7b49\u5e93\uff0c\u6211\u4eec\u80fd\u591f\u9ad8\u6548\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u5e76\u4e0b\u8f7d\u56fe\u7247\u3002\u4e3a\u4e86\u63d0\u9ad8\u722c\u866b\u7684\u7a33\u5b9a\u6027\u548c\u6548\u7387\uff0c\u6211\u4eec\u8fd8\u53ef\u4ee5\u5e94\u7528\u591a\u7ebf\u7a0b\u6280\u672f\u3001\u5f02\u5e38\u5904\u7406\u4ee5\u53ca\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236\u3002\u65e0\u8bba\u662f\u4e2a\u4eba\u9879\u76ee\u8fd8\u662f\u4f01\u4e1a\u5e94\u7528\uff0cPython\u722c\u866b\u90fd\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u81ea\u52a8\u5316\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n \u5982\u4f55\u4f7f\u7528Python\u722c\u866b\u6293\u53d6\u7f51\u9875\u4e2d\u7684\u56fe\u7247\uff1f<\/strong> \u6293\u53d6\u56fe\u7247\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong> \u6709\u4ec0\u4e48\u5de5\u5177\u6216\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u66f4\u9ad8\u6548\u5730\u722c\u53d6\u56fe\u7247\uff1f<\/strong>
Python\u722c\u866b\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528requests\u5e93\u83b7\u53d6\u9875\u9762\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u7ed3\u6784\u3001\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u6216CSS\u9009\u62e9\u5668\u63d0\u53d6\u56fe\u7247URL\u3001\u4f7f\u7528os\u5e93\u7ba1\u7406\u6587\u4ef6\u5b58\u50a8\u3001\u7ed3\u5408urllib\u5e93\u4e0b\u8f7d\u56fe\u7247<\/strong>\u3002\u5728\u8fd9\u4e9b\u6b65\u9aa4\u4e2d\uff0c\u6700\u5173\u952e\u7684\u662f\u63d0\u53d6\u56fe\u7247URL\u7684\u8fc7\u7a0b\uff0c\u56e0\u4e3a\u7f51\u9875\u4e0a\u7684\u56fe\u7247\u901a\u5e38\u5d4c\u5165\u5728\u590d\u6742\u7684HTML\u7ed3\u6784\u4e2d\u3002\u5229\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u7684HTML\u7ed3\u6784\uff0c\u53ef\u4ee5\u8ba9\u6211\u4eec\u8f7b\u677e\u627e\u5230\u9700\u8981\u7684\u56fe\u7247\u6807\u7b7e\u3002\u7136\u540e\uff0c\u901a\u8fc7\u63d0\u53d6\u6807\u7b7e\u4e2d\u7684src\u5c5e\u6027\uff0c\u6211\u4eec\u4fbf\u80fd\u591f\u83b7\u53d6\u56fe\u7247\u7684URL\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528urllib\u5e93\u7684urlretrieve\u65b9\u6cd5\u4e0b\u8f7d\u56fe\u7247\uff0c\u5e76\u7528os\u5e93\u5c06\u5176\u5b58\u50a8\u5728\u672c\u5730\u6307\u5b9a\u7684\u76ee\u5f55\u4e2d\u3002\u6b64\u5916\uff0c\u4e3a\u63d0\u9ad8\u722c\u866b\u7684\u6548\u7387\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u591a\u7ebf\u7a0b\u6280\u672f\uff0c\u5e76\u7ed3\u5408\u5f02\u5e38\u5904\u7406\u673a\u5236\u6765\u589e\u5f3a\u7a0b\u5e8f\u7684\u7a33\u5b9a\u6027\u3002<\/p>\n<\/p>\n\n
\n
\u6807\u7b7e\u5d4c\u5165\uff0c\u6211\u4eec\u9700\u8981\u627e\u5230\u8fd9\u4e9b\u6807\u7b7e\u5e76\u63d0\u53d6src\u5c5e\u6027\u7684\u503c\u3002<\/p>\n<\/p>\n
\n
\u6807\u7b7e<\/li>\n<\/ol>\n
\u6807\u7b7e\u3002\u8fd9\u4e2a\u65b9\u6cd5\u4f1a\u8fd4\u56de\u4e00\u4e2a\u5305\u542b\u6240\u6709
\u6807\u7b7e\u7684\u5217\u8868\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n\n
\u6807\u7b7e\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u8bbf\u95ee\u6807\u7b7e\u7684src\u5c5e\u6027\u6765\u83b7\u53d6\u56fe\u7247\u7684URL\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u6709\u4e9b\u56fe\u7247\u7684URL\u53ef\u80fd\u662f\u76f8\u5bf9\u8def\u5f84\uff0c\u9700\u8981\u8f6c\u6362\u4e3a\u7edd\u5bf9\u8def\u5f84\u3002<\/p>\n<\/p>\n
img_urls = [img['src'] for img in img_tags if 'src' in img.attrs]<\/p>\n\n
import urllib.request<\/p>\n\n
\n
from concurrent.futures import ThreadPoolExecutor<\/p>\n\n
import os<\/p>\n\n
def download_image(img_url):<\/p>\n\n
headers = {<\/p>\n\n
proxies = {<\/p>\n\n
from selenium import webdriver<\/p>\n\n
\u6807\u7b7e\u5d4c\u5165\uff0c\u4e14src\u5c5e\u6027\u5305\u542b\u56fe\u7247\u7684URL\u3002<\/p>\n<\/p>\n
\n
import requests<\/p>\n\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/strong><\/h2>\n
\u521b\u5efa\u5b58\u50a8\u76ee\u5f55<\/strong><\/h2>\n
\u8bbf\u95eeUnsplash\u9996\u9875<\/strong><\/h2>\n
\u67e5\u627e\u5e76\u4e0b\u8f7d\u56fe\u7247<\/strong><\/h2>\n
\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
\u5728\u4f7f\u7528Python\u722c\u866b\u6293\u53d6\u7f51\u9875\u56fe\u7247\u65f6\uff0c\u901a\u5e38\u4f1a\u4f7f\u7528\u5e93\u5982Requests\u548cBeautifulSoup\u3002\u9996\u5148\uff0c\u901a\u8fc7Requests\u5e93\u5411\u76ee\u6807\u7f51\u7ad9\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\uff0c\u627e\u5230\u56fe\u7247\u7684URL\u3002\u63a5\u7740\uff0c\u53ef\u4ee5\u4f7f\u7528Requests\u5e93\u4e0b\u8f7d\u8fd9\u4e9b\u56fe\u7247\uff0c\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u5939\u4e2d\u3002\u6ce8\u610f\uff0c\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u548c\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u3002<\/p>\n
\u5728\u6293\u53d6\u56fe\u7247\u4e4b\u524d\uff0c\u4e86\u89e3\u5e76\u9075\u5b88\u7248\u6743\u6cd5\u89c4\u975e\u5e38\u91cd\u8981\u3002\u8bb8\u591a\u7f51\u7ad9\u4e0a\u7684\u56fe\u7247\u53d7\u7248\u6743\u4fdd\u62a4\uff0c\u672a\u7ecf\u5141\u8bb8\u4e0b\u8f7d\u548c\u4f7f\u7528\u8fd9\u4e9b\u56fe\u7247\u53ef\u80fd\u4f1a\u5bfc\u81f4\u6cd5\u5f8b\u95ee\u9898\u3002\u6b64\u5916\uff0c\u5c0a\u91cd\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\uff0c\u786e\u4fdd\u4e0d\u4f1a\u5bf9\u7f51\u7ad9\u9020\u6210\u8fc7\u591a\u7684\u8d1f\u62c5\uff0c\u5408\u7406\u63a7\u5236\u722c\u866b\u8bf7\u6c42\u7684\u9891\u7387\u3002<\/p>\n
\u9664\u4e86Requests\u548cBeautifulSoup\uff0cScrapy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u5927\u89c4\u6a21\u6293\u53d6\u3002\u5b83\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u6570\u636e\u63d0\u53d6\u548c\u5904\u7406\u529f\u80fd\uff0c\u5141\u8bb8\u4f60\u5728\u6293\u53d6\u8fc7\u7a0b\u4e2d\u8fdb\u884c\u56fe\u7247\u4e0b\u8f7d\u548c\u5b58\u50a8\u3002\u6b64\u5916\uff0cPillow\u5e93\u53ef\u4ee5\u7528\u4e8e\u5904\u7406\u4e0b\u8f7d\u540e\u7684\u56fe\u7247\uff0c\u6bd4\u5982\u8c03\u6574\u5927\u5c0f\u3001\u683c\u5f0f\u8f6c\u6362\u7b49\uff0c\u63d0\u5347\u56fe\u7247\u7684\u4f7f\u7528\u4f53\u9a8c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5f00\u5934\u6bb5\u843d:Python\u722c\u866b\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528requests\u5e93\u83b7\u53d6\u9875\u9762\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTM […]","protected":false},"author":3,"featured_media":1008616,"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\/1008607"}],"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=1008607"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1008607\/revisions"}],"predecessor-version":[{"id":1008618,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1008607\/revisions\/1008618"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1008616"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1008607"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1008607"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1008607"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}