{"id":2931,"date":"2025-03-18T00:47:46","date_gmt":"2025-03-17T16:47:46","guid":{"rendered":"https:\/\/www.laixuexila.com\/?p=2931"},"modified":"2025-03-18T00:47:46","modified_gmt":"2025-03-17T16:47:46","slug":"python-%e7%88%ac%e8%99%ab-beautifulsoup","status":"publish","type":"post","link":"https:\/\/www.laixuexila.com\/index.php\/2025\/03\/18\/python-%e7%88%ac%e8%99%ab-beautifulsoup\/","title":{"rendered":"Python \u722c\u866b &#8211; BeautifulSoup"},"content":{"rendered":"\n<p><code>BeautifulSoup<\/code> \u662f Python \u4e2d\u4e00\u4e2a\u975e\u5e38\u6d41\u884c\u4e14\u5f3a\u5927\u7684\u7f51\u9875\u89e3\u6790\u5e93\uff0c\u5e7f\u6cdb\u7528\u4e8e\u7f51\u9875\u6293\u53d6\uff08Web Scraping\uff09\u3002\u5b83\u80fd\u591f\u4ece HTML \u6216 XML \u6587\u4ef6\u4e2d\u63d0\u53d6\u6570\u636e\u5e76\u8fdb\u884c\u89e3\u6790\uff0c\u5904\u7406\u4e0d\u89c4\u8303\u7684\u7f51\u9875\u7ed3\u6784\u548c\u7f16\u7801\u95ee\u9898\uff0c\u4f7f\u5f97\u7f51\u9875\u6293\u53d6\u53d8\u5f97\u66f4\u52a0\u7b80\u5355\u548c\u9ad8\u6548\u3002<code>BeautifulSoup<\/code> \u914d\u5408 <code>requests<\/code> \u5e93\u4e00\u8d77\u4f7f\u7528\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u4fe1\u606f\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">1. <strong>\u5b89\u88c5 BeautifulSoup<\/strong><\/h2>\n\n\n\n<p>\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5 <code>BeautifulSoup<\/code> \u4ee5\u53ca\u5176\u4f9d\u8d56\u7684\u89e3\u6790\u5668 <code>lxml<\/code> \u6216 <code>html.parser<\/code>\u3002\u53ef\u4ee5\u901a\u8fc7 <code>pip<\/code> \u5b89\u88c5\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>pip install beautifulsoup4\npip install lxml  # \u6216\u8005\u5b89\u88c5 html.parser (\u65e0\u9700\u5355\u72ec\u5b89\u88c5)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">2. <strong>\u57fa\u7840\u4f7f\u7528<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">2.1 <strong>\u8bf7\u6c42\u7f51\u9875<\/strong><\/h3>\n\n\n\n<p>\u4f7f\u7528 <code>requests<\/code> \u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u4f20\u9012\u7ed9 <code>BeautifulSoup<\/code> \u8fdb\u884c\u89e3\u6790\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import requests\nfrom bs4 import BeautifulSoup\n\n# \u8bf7\u6c42\u7f51\u9875\u5185\u5bb9\nurl = 'https:\/\/example.com'\nresponse = requests.get(url)\n\n# \u4f7f\u7528 BeautifulSoup \u89e3\u6790 HTML \u5185\u5bb9\nsoup = BeautifulSoup(response.text, 'html.parser')\n\n# \u6253\u5370\u7f51\u9875\u7684\u683c\u5f0f\u5316\u5185\u5bb9\nprint(soup.prettify())  # prettify() \u4f1a\u683c\u5f0f\u5316\u8f93\u51fa HTML \u5185\u5bb9<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">3. <strong>\u57fa\u672c\u89e3\u6790\u65b9\u6cd5<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">3.1 <strong>\u83b7\u53d6\u5355\u4e00\u5143\u7d20<\/strong><\/h3>\n\n\n\n<p><code>BeautifulSoup<\/code> \u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u83b7\u53d6\u9875\u9762\u4e2d\u7684\u5143\u7d20\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u901a\u8fc7\u6807\u7b7e\u540d\u83b7\u53d6<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  # \u83b7\u53d6\u7b2c\u4e00\u4e2a &lt;a&gt; \u6807\u7b7e\n  a_tag = soup.find('a')\n  print(a_tag)<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u901a\u8fc7\u6807\u7b7e\u5c5e\u6027\u83b7\u53d6<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  # \u83b7\u53d6\u5e26\u6709\u7279\u5b9a id \u5c5e\u6027\u7684\u6807\u7b7e\n  div_tag = soup.find('div', {'id': 'main'})\n  print(div_tag)<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">3.2 <strong>\u83b7\u53d6\u591a\u4e2a\u5143\u7d20<\/strong><\/h3>\n\n\n\n<p>\u5982\u679c\u7f51\u9875\u4e2d\u6709\u591a\u4e2a\u76f8\u540c\u7684\u6807\u7b7e\uff0c\u53ef\u4ee5\u4f7f\u7528 <code>find_all()<\/code> \u83b7\u53d6\u5b83\u4eec\u7684\u96c6\u5408\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u83b7\u53d6\u6240\u6709 <a>\u6807\u7b7e<\/a><\/strong><a>\uff1a<\/a><\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  a_tags = soup.find_all('a')\n  for tag in a_tags:\n      print(tag)<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u901a\u8fc7\u7c7b\u540d\u83b7\u53d6\u591a\u4e2a\u5143\u7d20<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  divs = soup.find_all('div', class_='content')\n  for div in divs:\n      print(div)<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">3.3 <strong>\u83b7\u53d6\u5143\u7d20\u7684\u5c5e\u6027<\/strong><\/h3>\n\n\n\n<p>\u901a\u8fc7 <code>get()<\/code> \u65b9\u6cd5\uff0c\u53ef\u4ee5\u8bbf\u95ee\u5143\u7d20\u7684\u5c5e\u6027\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u83b7\u53d6 href \u5c5e\u6027<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  first_a = soup.find('a')\n  href = first_a.get('href')\n  print(href)<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u83b7\u53d6\u5143\u7d20\u7684\u5176\u4ed6\u5c5e\u6027<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  img_tag = soup.find('img')\n  img_src = img_tag.get('src')\n  print(img_src)<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">3.4 <strong>\u83b7\u53d6\u6587\u672c\u5185\u5bb9<\/strong><\/h3>\n\n\n\n<p>\u53ef\u4ee5\u4f7f\u7528 <code>.text<\/code> \u6216 <code>.string<\/code> \u83b7\u53d6\u6807\u7b7e\u4e2d\u7684\u7eaf\u6587\u672c\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u83b7\u53d6\u6807\u7b7e\u4e2d\u7684\u6587\u672c<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  h1_tag = soup.find('h1')\n  print(h1_tag.text)<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u83b7\u53d6\u67d0\u4e2a\u5b50\u6807\u7b7e\u7684\u6587\u672c<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  div_tag = soup.find('div', {'class': 'content'})\n  paragraph = div_tag.find('p')\n  print(paragraph.text)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">4. <strong>\u9ad8\u7ea7\u7528\u6cd5<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">4.1 <strong>CSS \u9009\u62e9\u5668<\/strong><\/h3>\n\n\n\n<p><code>BeautifulSoup<\/code> \u5141\u8bb8\u4f7f\u7528 CSS \u9009\u62e9\u5668\u6765\u5b9a\u4f4d\u5143\u7d20\uff0c\u8fd9\u79cd\u65b9\u6cd5\u975e\u5e38\u5f3a\u5927\u548c\u7075\u6d3b\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u901a\u8fc7 CSS \u9009\u62e9\u5668\u67e5\u627e\u5143\u7d20<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  # \u67e5\u627e\u6240\u6709 class \u4e3a 'item' \u7684 &lt;div&gt; \u6807\u7b7e\n  items = soup.select('div.item')\n  for item in items:\n      print(item)<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u901a\u8fc7\u5b50\u5143\u7d20\u9009\u62e9<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  # \u67e5\u627e class \u4e3a 'content' \u7684 div \u4e0b\u7684\u6240\u6709 &lt;p&gt; \u6807\u7b7e\n  paragraphs = soup.select('div.content p')\n  for p in paragraphs:\n      print(p.text)<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">4.2 <strong>NavigableString \u548c Comment<\/strong><\/h3>\n\n\n\n<p><code>BeautifulSoup<\/code> \u63d0\u4f9b\u4e86 <code>NavigableString<\/code> \u7c7b\u578b\uff0c\u5b83\u8868\u793a\u7f51\u9875\u4e2d\u67d0\u4e9b\u6587\u672c\u5185\u5bb9\u3002\u53ef\u4ee5\u7528\u6765\u5904\u7406\u6587\u672c\u8282\u70b9\u3002\u6b64\u5916\uff0c\u5b83\u8fd8\u652f\u6301 <code>Comment<\/code> \u7c7b\u578b\uff0c\u4e13\u95e8\u7528\u4e8e\u5904\u7406 HTML \u6ce8\u91ca\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u83b7\u53d6\u7f51\u9875\u6ce8\u91ca<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n<pre class=\"wp-block-code\"><code>  comment = soup.find(string=lambda text: isinstance(text, Comment))\n  print(comment)<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">4.3 <strong>\u5d4c\u5957\u89e3\u6790<\/strong><\/h3>\n\n\n\n<p><code>BeautifulSoup<\/code> \u652f\u6301\u5c42\u7ea7\u7ed3\u6784\u7684\u89e3\u6790\uff0c\u5141\u8bb8\u5d4c\u5957\u67e5\u627e\u6807\u7b7e\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u67e5\u627e &lt;div class='content'&gt; \u4e0b\u7684\u7b2c\u4e00\u4e2a &lt;p&gt; \u6807\u7b7e\ndiv = soup.find('div', class_='content')\np_tag = div.find('p')\nprint(p_tag.text)<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">4.4 <strong>\u9012\u5f52\u67e5\u627e\u5143\u7d20<\/strong><\/h3>\n\n\n\n<p><code>find_all()<\/code> \u65b9\u6cd5\u8fd8\u53ef\u4ee5\u901a\u8fc7\u9012\u5f52\u67e5\u627e\u5b50\u5143\u7d20\uff0c\u76f4\u5230\u627e\u5230\u7b26\u5408\u6761\u4ef6\u7684\u6240\u6709\u5143\u7d20\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u67e5\u627e\u6240\u6709\u5d4c\u5957\u5728 &lt;div&gt; \u4e2d\u7684 &lt;p&gt; \u6807\u7b7e\ndiv_tag = soup.find('div')\np_tags = div_tag.find_all('p', recursive=True)\nfor p in p_tags:\n    print(p.text)<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">4.5 <strong>\u6b63\u5219\u8868\u8fbe\u5f0f<\/strong><\/h3>\n\n\n\n<p>\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u53ef\u4ee5\u7075\u6d3b\u5730\u5339\u914d\u6807\u7b7e\u7684\u5c5e\u6027\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import re\n# \u67e5\u627e\u6240\u6709 class \u540d\u5b57\u4e2d\u5305\u542b 'item' \u7684\u6807\u7b7e\nitems = soup.find_all('div', class_=re.compile('.*item.*'))\nfor item in items:\n    print(item)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">5. <strong>\u5904\u7406\u590d\u6742\u7684 HTML \u7ed3\u6784<\/strong><\/h2>\n\n\n\n<p>\u5728\u5b9e\u9645\u6293\u53d6\u8fc7\u7a0b\u4e2d\uff0c\u7f51\u9875\u7684 HTML \u7ed3\u6784\u53ef\u80fd\u4f1a\u975e\u5e38\u590d\u6742\uff0c\u5305\u542b\u5927\u91cf\u7684\u5d4c\u5957\u548c\u591a\u4f59\u7684\u6807\u7b7e\u3002\u6b64\u65f6\uff0c<code>BeautifulSoup<\/code> \u53ef\u4ee5\u5e2e\u52a9\u6e05\u7406\u548c\u63d0\u53d6\u6211\u4eec\u9700\u8981\u7684\u6570\u636e\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">5.1 <strong>\u53bb\u9664 HTML \u6807\u7b7e<\/strong><\/h3>\n\n\n\n<p><code>BeautifulSoup<\/code> \u63d0\u4f9b\u4e86 <code>.get_text()<\/code> \u65b9\u6cd5\u6765\u53bb\u9664 HTML \u6807\u7b7e\uff0c\u53ea\u4fdd\u7559\u6587\u672c\u5185\u5bb9\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u83b7\u53d6\u6ca1\u6709 HTML \u6807\u7b7e\u7684\u7eaf\u6587\u672c\ntext = soup.get_text()\nprint(text)<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">5.2 <strong>\u6e05\u7406\u4e0d\u9700\u8981\u7684\u6807\u7b7e<\/strong><\/h3>\n\n\n\n<p>\u53ef\u4ee5\u4f7f\u7528 <code>.decompose()<\/code> \u65b9\u6cd5\u5220\u9664\u4e0d\u9700\u8981\u7684\u6807\u7b7e\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u5220\u9664\u6240\u6709 &lt;script&gt; \u6807\u7b7e\nfor script in soup.find_all('script'):\n    script.decompose()<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">5.3 <strong>\u89e3\u6790\u590d\u6742\u7684\u8868\u683c<\/strong><\/h3>\n\n\n\n<p><code>BeautifulSoup<\/code> \u53ef\u4ee5\u65b9\u4fbf\u5730\u5904\u7406\u7f51\u9875\u4e2d\u7684\u8868\u683c\u7ed3\u6784\u3002\u901a\u8fc7 <code>find_all('tr')<\/code> \u65b9\u6cd5\u53ef\u4ee5\u63d0\u53d6\u6240\u6709\u884c\uff0c\u8fdb\u4e00\u6b65\u63d0\u53d6\u6bcf\u4e00\u884c\u4e2d\u7684\u5355\u5143\u683c\u6570\u636e\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u83b7\u53d6\u8868\u683c\u4e2d\u6240\u6709\u7684\u884c\ntable = soup.find('table')\nrows = table.find_all('tr')\nfor row in rows:\n    cols = row.find_all('td')\n    cols_text = &#91;col.text for col in cols]\n    print(cols_text)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">6. <strong>\u603b\u7ed3<\/strong><\/h2>\n\n\n\n<p><code>BeautifulSoup<\/code> \u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684\u7f51\u9875\u89e3\u6790\u5de5\u5177\uff0c\u9002\u5408\u7528\u4e8e\u5904\u7406 HTML \u548c XML \u6570\u636e\uff0c\u7279\u522b\u662f\u5728\u7f51\u9875\u6293\u53d6\u65f6\u975e\u5e38\u6709\u7528\u3002\u5b83\u4e0e <code>requests<\/code> \u5e93\u914d\u5408\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6240\u9700\u7684\u5185\u5bb9\uff0c\u652f\u6301\u591a\u79cd\u67e5\u627e\u65b9\u6cd5\uff0c\u5982\u6807\u7b7e\u540d\u67e5\u627e\u3001\u5c5e\u6027\u67e5\u627e\u3001CSS \u9009\u62e9\u5668\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u7b49\u3002\u901a\u8fc7\u5b83\uff0c\u5f00\u53d1\u8005\u80fd\u591f\u8f7b\u677e\u5730\u4ece\u4e0d\u89c4\u8303\u7684\u7f51\u9875\u4e2d\u63d0\u53d6\u51fa\u7ed3\u6784\u5316\u7684\u6570\u636e\u3002<\/p>\n\n\n\n<p>\u5e38\u89c1\u7684\u5e94\u7528\u573a\u666f\u5305\u62ec\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u7f51\u9875\u5185\u5bb9\u6293\u53d6<\/li>\n\n\n\n<li>\u6570\u636e\u6e05\u6d17\u548c\u63d0\u53d6<\/li>\n\n\n\n<li>\u81ea\u52a8\u5316\u62a5\u544a\u751f\u6210<\/li>\n\n\n\n<li>\u7f51\u9875\u6570\u636e\u5206\u6790<\/li>\n<\/ul>\n\n\n\n<p>\u5728\u5b9e\u9645\u4f7f\u7528\u65f6\uff0c\u7ed3\u5408 <code>requests<\/code> \u548c <code>BeautifulSoup<\/code>\uff0c\u4f60\u53ef\u4ee5\u9ad8\u6548\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u548c\u5904\u7406\u4fe1\u606f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>BeautifulSoup \u662f Python \u4e2d\u4e00\u4e2a\u975e\u5e38\u6d41\u884c\u4e14\u5f3a\u5927\u7684\u7f51\u9875\u89e3\u6790\u5e93\uff0c\u5e7f\u6cdb\u7528\u4e8e\u7f51\u9875\u6293\u53d6\uff08Web Sc [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2932,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[79],"tags":[],"class_list":["post-2931","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-python-3-"],"_links":{"self":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/2931","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/comments?post=2931"}],"version-history":[{"count":1,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/2931\/revisions"}],"predecessor-version":[{"id":2933,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/2931\/revisions\/2933"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/media\/2932"}],"wp:attachment":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/media?parent=2931"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/categories?post=2931"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/tags?post=2931"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}