如何将 HTML 拆分
将 HTML 文档拆分为可管理的块对于各种文本处理任务至关重要，例如自然语言处理、搜索索引等。在本指南中，我们将探讨 LangChain 提供的三种不同的文本分割器，您可以使用它们有效地拆分 HTML 内容：
这些分割器各自具有独特的特性和使用场景。本指南将帮助您了解它们之间的区别、为何选择其中一种而非其他，以及如何有效地使用它们。
%pip install -qU langchain-text-splitters
概述分割器
HTMLHeaderTextSplitter
信息
当您需要根据标题保留文档的层次结构时，此方法非常有用。
描述: 基于标题标签（例如，<h1>, <h2>, <h3>等）分割HTML文本，并为每个与给定块相关的标题添加元数据。
能力:
- 在 HTML 元素级别分割文本。
- 保留文档结构中编码的上下文丰富信息。
- 可以按元素返回块，或合并具有相同元数据的元素。
HTMLSectionSplitter
信息
当您需要将 HTML 文档拆分为更大的部分（例如 <section>、<div> 或自定义定义的章节）时，此方法非常有用。
描述: 类似于 HTMLHeaderTextSplitter，但专注于根据指定标签将 HTML 分割为各个部分。
能力:
- 使用 XSLT 转换来检测和分割章节。
- 内部使用
RecursiveCharacterTextSplitter表示大型区块。 - 考虑字体大小以确定章节。
HTML语义保留分割器
信息
当您需要确保结构化元素不被分割到不同的块中，从而保留上下文相关性时，此方案非常适用。
描述: 将 HTML 内容拆分为可管理的块，同时保留重要元素（如表格、列表和其他 HTML 组件）的语义结构。
能力:
- 保留表格、列表和其他指定的 HTML 元素。
- 允许为特定的 HTML 标签自定义处理程序。
- 确保文档的语义含义得以保留。
- 内置的标准化与停用词移除
选择正确的分割器
- 使用
HTMLHeaderTextSplitter当: 您需要根据 HTML 文档的标题层次结构拆分文档，并维护关于标题的元数据。 - 使用
HTMLSectionSplitter当: 您需要将文档拆分为更大、更通用的部分，可能是基于自定义标签或字体大小。 - 使用
HTMLSemanticPreservingSplitter当: 您需要将文档拆分为块，同时保留语义元素（如表格和列表），确保它们不被拆分且上下文得以保持。
| 功能 | HTMLHeaderTextSplitter | HTMLSectionSplitter | HTML语义保留分割器 |
|---|---|---|---|
| Splits based on headers | Yes | Yes | Yes |
| Preserves semantic elements (tables, lists) | No | No | Yes |
| Adds metadata for headers | Yes | Yes | Yes |
| Custom handlers for HTML tags | No | No | Yes |
| Preserves media (images, videos) | No | No | Yes |
| Considers font sizes | No | Yes | No |
| Uses XSLT transformations | No | Yes | No |
示例 HTML 文档
让我们使用以下 HTML 文档作为示例：
html_string = """
<!DOCTYPE html>
<html lang='en'>
<head>
<meta charset='UTF-8'>
<meta name='viewport' content='width=device-width, initial-scale=1.0'>
<title>Fancy Example HTML Page</title>
</head>
<body>
<h1>Main Title</h1>
<p>This is an introductory paragraph with some basic content.</p>
<h2>Section 1: Introduction</h2>
<p>This section introduces the topic. Below is a list:</p>
<ul>
<li>First item</li>
<li>Second item</li>
<li>Third item with <strong>bold text</strong> and <a href='#'>a link</a></li>
</ul>
<h3>Subsection 1.1: Details</h3>
<p>This subsection provides additional details. Here's a table:</p>
<table border='1'>
<thead>
<tr>
<th>Header 1</th>
<th>Header 2</th>
<th>Header 3</th>
</tr>
</thead>
<tbody>
<tr>
<td>Row 1, Cell 1</td>
<td>Row 1, Cell 2</td>
<td>Row 1, Cell 3</td>
</tr>
<tr>
<td>Row 2, Cell 1</td>
<td>Row 2, Cell 2</td>
<td>Row 2, Cell 3</td>
</tr>
</tbody>
</table>
<h2>Section 2: Media Content</h2>
<p>This section contains an image and a video:</p>
<img src='example_image_link.mp4' alt='Example Image'>
<video controls width='250' src='example_video_link.mp4' type='video/mp4'>
Your browser does not support the video tag.
</video>
<h2>Section 3: Code Example</h2>
<p>This section contains a code block:</p>
<pre><code data-lang="html">
<div>
<p>This is a paragraph inside a div.</p>
</div>
</code></pre>
<h2>Conclusion</h2>
<p>This is the conclusion of the document.</p>
</body>
</html>
"""
使用 HTMLHeaderTextSplitter
HTMLHeaderTextSplitter 是一种“结构感知”的 文本分割器，它按 HTML 元素级别分割文本，并为每个包含相关标题信息的块添加元数据。它可以逐个元素返回块，也可以将具有相同元数据的元素组合起来，其目标是：(a) 保持相关文本在语义上大致分组；(b) 保留文档结构中编码的上下文丰富信息。它可与其他文本分割器配合使用，作为分块流程的一部分。
它类似于用于 markdown 文件的 MarkdownHeaderTextSplitter。
要指定在哪些标题处进行分割，请在实例化 HTMLHeaderTextSplitter 时指定 headers_to_split_on，如下所示。
from langchain_text_splitters import HTMLHeaderTextSplitter
headers_to_split_on = [
("h1", "Header 1"),
("h2", "Header 2"),
("h3", "Header 3"),
]
html_splitter = HTMLHeaderTextSplitter(headers_to_split_on)
html_header_splits = html_splitter.split_text(html_string)
html_header_splits
API 参考:HTMLHeaderTextSplitter
[Document(metadata={'Header 1': 'Main Title'}, page_content='This is an introductory paragraph with some basic content.'),
Document(metadata={'Header 1': 'Main Title', 'Header 2': 'Section 1: Introduction'}, page_content='This section introduces the topic. Below is a list: \nFirst item Second item Third item with bold text and a link'),
Document(metadata={'Header 1': 'Main Title', 'Header 2': 'Section 1: Introduction', 'Header 3': 'Subsection 1.1: Details'}, page_content="This subsection provides additional details. Here's a table:"),
Document(metadata={'Header 1': 'Main Title', 'Header 2': 'Section 2: Media Content'}, page_content='This section contains an image and a video:'),
Document(metadata={'Header 1': 'Main Title', 'Header 2': 'Section 3: Code Example'}, page_content='This section contains a code block:'),
Document(metadata={'Header 1': 'Main Title', 'Header 2': 'Conclusion'}, page_content='This is the conclusion of the document.')]
要返回每个元素及其关联的表头，请在实例化HTMLHeaderTextSplitter时指定return_each_element=True：
html_splitter = HTMLHeaderTextSplitter(
headers_to_split_on,
return_each_element=True,
)
html_header_splits_elements = html_splitter.split_text(html_string)
与上述相比，其中元素按其标题聚合：
for element in html_header_splits[:2]:
print(element)
page_content='This is an introductory paragraph with some basic content.' metadata={'Header 1': 'Main Title'}
page_content='This section introduces the topic. Below is a list:
First item Second item Third item with bold text and a link' metadata={'Header 1': 'Main Title', 'Header 2': 'Section 1: Introduction'}
现在每个元素都作为独立的 Document 返回：
for element in html_header_splits_elements[:3]:
print(element)
page_content='This is an introductory paragraph with some basic content.' metadata={'Header 1': 'Main Title'}
page_content='This section introduces the topic. Below is a list:' metadata={'Header 1': 'Main Title', 'Header 2': 'Section 1: Introduction'}
page_content='First item Second item Third item with bold text and a link' metadata={'Header 1': 'Main Title', 'Header 2': 'Section 1: Introduction'}
如何从 URL 或 HTML 文件进行分割:
要直接从 URL 读取，请将 URL 字符串传递给 split_text_from_url 方法。
同样，本地 HTML 文件也可以传递给 split_text_from_file 方法。
url = "https://plato.stanford.edu/entries/goedel/"
headers_to_split_on = [
("h1", "Header 1"),
("h2", "Header 2"),
("h3", "Header 3"),
("h4", "Header 4"),
]
html_splitter = HTMLHeaderTextSplitter(headers_to_split_on)
# for local file use html_splitter.split_text_from_file(<path_to_file>)
html_header_splits = html_splitter.split_text_from_url(url)
如何限制块大小：
HTMLHeaderTextSplitter，它基于 HTML 标题进行分割，可以与另一个基于字符长度限制分割的分割器组合使用，例如 RecursiveCharacterTextSplitter。
这可以通过第二个分割器的 .split_documents 方法完成：
from langchain_text_splitters import RecursiveCharacterTextSplitter
chunk_size = 500
chunk_overlap = 30
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=chunk_size, chunk_overlap=chunk_overlap
)
# Split
splits = text_splitter.split_documents(html_header_splits)
splits[80:85]
API 参考:递归字符文本分割器
[Document(metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.1 The First Incompleteness Theorem'}, page_content='We see that Gödel first tried to reduce the consistency problem for analysis to that of arithmetic. This seemed to require a truth definition for arithmetic, which in turn led to paradoxes, such as the Liar paradox (“This sentence is false”) and Berry’s paradox (“The least number not defined by an expression consisting of just fourteen English words”). Gödel then noticed that such paradoxes would not necessarily arise if truth were replaced by provability. But this means that arithmetic truth'),
Document(metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.1 The First Incompleteness Theorem'}, page_content='means that arithmetic truth and arithmetic provability are not co-extensive — whence the First Incompleteness Theorem.'),
Document(metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.1 The First Incompleteness Theorem'}, page_content='This account of Gödel’s discovery was told to Hao Wang very much after the fact; but in Gödel’s contemporary correspondence with Bernays and Zermelo, essentially the same description of his path to the theorems is given. (See Gödel 2003a and Gödel 2003b respectively.) From those accounts we see that the undefinability of truth in arithmetic, a result credited to Tarski, was likely obtained in some form by Gödel by 1931. But he neither publicized nor published the result; the biases logicians'),
Document(metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.1 The First Incompleteness Theorem'}, page_content='result; the biases logicians had expressed at the time concerning the notion of truth, biases which came vehemently to the fore when Tarski announced his results on the undefinability of truth in formal systems 1935, may have served as a deterrent to Gödel’s publication of that theorem.'),
Document(metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.2 The proof of the First Incompleteness Theorem'}, page_content='We now describe the proof of the two theorems, formulating Gödel’s results in Peano arithmetic. Gödel himself used a system related to that defined in Principia Mathematica, but containing Peano arithmetic. In our presentation of the First and Second Incompleteness Theorems we refer to Peano arithmetic as P, following Gödel’s notation.')]
局限性
从一个 HTML 文档到另一个文档，其结构可能存在相当大的差异。虽然 HTMLHeaderTextSplitter 会尝试将任何给定块的所有“相关”标题附加上去，但它有时会遗漏某些标题。例如，该算法假设一种信息层级结构，其中标题始终位于相关联文本的“上方”节点，即前兄弟节点、祖先节点或它们的组合。在以下新闻文章（截至本文档撰写时）中，文档的结构使得顶级标题的文本虽然被标记为"h1"，却与我们预期它应位于“上方”的文本元素处于一个不同的子树中——因此我们可以观察到"h1"元素及其关联文本并未出现在块的元数据中（但在适用情况下，我们会看到"h2"及其关联文本）：
url = "https://www.cnn.com/2023/09/25/weather/el-nino-winter-us-climate/index.html"
headers_to_split_on = [
("h1", "Header 1"),
("h2", "Header 2"),
]
html_splitter = HTMLHeaderTextSplitter(headers_to_split_on)
html_header_splits = html_splitter.split_text_from_url(url)
print(html_header_splits[1].page_content[:500])
No two El Niño winters are the same, but many have temperature and precipitation trends in common.
Average conditions during an El Niño winter across the continental US.
One of the major reasons is the position of the jet stream, which often shifts south during an El Niño winter. This shift typically brings wetter and cooler weather to the South while the North becomes drier and warmer, according to NOAA.
Because the jet stream is essentially a river of air that storms flow through, they c
使用 HTMLSectionSplitter
与 HTMLHeaderTextSplitter 的概念类似，HTMLSectionSplitter 是一个“结构感知”的 文本分割器，它按元素级别分割文本，并为每个标题添加与任何给定块“相关”的元数据。它允许您按章节分割 HTML。
它可以逐个元素返回块，或将具有相同元数据的元素组合在一起，其目标是 (a) 保持相关文本在语义上（大致）分组，以及 (b) 保留文档结构中编码的上下文丰富信息。
使用 xslt_path 提供绝对路径以转换 HTML，使其能够根据提供的标签检测章节。默认情况下，将使用 data_connection/document_transformers 目录中的 converting_to_header.xslt 文件。这是为了将 HTML 转换为更易于检测章节的格式/布局。例如，基于字体大小的 span 可以转换为标题标签，以便被识别为章节。
如何将 HTML 字符串拆分:
from langchain_text_splitters import HTMLSectionSplitter
headers_to_split_on = [
("h1", "Header 1"),
("h2", "Header 2"),
]
html_splitter = HTMLSectionSplitter(headers_to_split_on)
html_header_splits = html_splitter.split_text(html_string)
html_header_splits
API 参考:HTMLSectionSplitter
[Document(metadata={'Header 1': 'Main Title'}, page_content='Main Title \n This is an introductory paragraph with some basic content.'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content="Section 1: Introduction \n This section introduces the topic. Below is a list: \n \n First item \n Second item \n Third item with bold text and a link \n \n \n Subsection 1.1: Details \n This subsection provides additional details. Here's a table: \n \n \n \n Header 1 \n Header 2 \n Header 3 \n \n \n \n \n Row 1, Cell 1 \n Row 1, Cell 2 \n Row 1, Cell 3 \n \n \n Row 2, Cell 1 \n Row 2, Cell 2 \n Row 2, Cell 3"),
Document(metadata={'Header 2': 'Section 2: Media Content'}, page_content='Section 2: Media Content \n This section contains an image and a video: \n \n \n Your browser does not support the video tag.'),
Document(metadata={'Header 2': 'Section 3: Code Example'}, page_content='Section 3: Code Example \n This section contains a code block: \n \n <div>\n <p>This is a paragraph inside a div.</p>\n </div>'),
Document(metadata={'Header 2': 'Conclusion'}, page_content='Conclusion \n This is the conclusion of the document.')]
如何限制块大小：
HTMLSectionSplitter 可与其他文本分割器一起用作分块管道的一部分。当节大小大于块大小时，它在内部使用 RecursiveCharacterTextSplitter。它还考虑文本的字体大小，以确定基于确定的字体大小阈值是否为一个节。
from langchain_text_splitters import RecursiveCharacterTextSplitter
headers_to_split_on = [
("h1", "Header 1"),
("h2", "Header 2"),
("h3", "Header 3"),
]
html_splitter = HTMLSectionSplitter(headers_to_split_on)
html_header_splits = html_splitter.split_text(html_string)
chunk_size = 50
chunk_overlap = 5
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=chunk_size, chunk_overlap=chunk_overlap
)
# Split
splits = text_splitter.split_documents(html_header_splits)
splits
API 参考:递归字符文本分割器
[Document(metadata={'Header 1': 'Main Title'}, page_content='Main Title'),
Document(metadata={'Header 1': 'Main Title'}, page_content='This is an introductory paragraph with some'),
Document(metadata={'Header 1': 'Main Title'}, page_content='some basic content.'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content='Section 1: Introduction'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content='This section introduces the topic. Below is a'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content='is a list:'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content='First item \n Second item'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content='Third item with bold text and a link'),
Document(metadata={'Header 3': 'Subsection 1.1: Details'}, page_content='Subsection 1.1: Details'),
Document(metadata={'Header 3': 'Subsection 1.1: Details'}, page_content='This subsection provides additional details.'),
Document(metadata={'Header 3': 'Subsection 1.1: Details'}, page_content="Here's a table:"),
Document(metadata={'Header 3': 'Subsection 1.1: Details'}, page_content='Header 1 \n Header 2 \n Header 3'),
Document(metadata={'Header 3': 'Subsection 1.1: Details'}, page_content='Row 1, Cell 1 \n Row 1, Cell 2'),
Document(metadata={'Header 3': 'Subsection 1.1: Details'}, page_content='Row 1, Cell 3 \n \n \n Row 2, Cell 1'),
Document(metadata={'Header 3': 'Subsection 1.1: Details'}, page_content='Row 2, Cell 2 \n Row 2, Cell 3'),
Document(metadata={'Header 2': 'Section 2: Media Content'}, page_content='Section 2: Media Content'),
Document(metadata={'Header 2': 'Section 2: Media Content'}, page_content='This section contains an image and a video:'),
Document(metadata={'Header 2': 'Section 2: Media Content'}, page_content='Your browser does not support the video'),
Document(metadata={'Header 2': 'Section 2: Media Content'}, page_content='tag.'),
Document(metadata={'Header 2': 'Section 3: Code Example'}, page_content='Section 3: Code Example'),
Document(metadata={'Header 2': 'Section 3: Code Example'}, page_content='This section contains a code block: \n \n <div>'),
Document(metadata={'Header 2': 'Section 3: Code Example'}, page_content='<p>This is a paragraph inside a div.</p>'),
Document(metadata={'Header 2': 'Section 3: Code Example'}, page_content='</div>'),
Document(metadata={'Header 2': 'Conclusion'}, page_content='Conclusion'),
Document(metadata={'Header 2': 'Conclusion'}, page_content='This is the conclusion of the document.')]
使用 HTMLSemanticPreservingSplitter
HTMLSemanticPreservingSplitter 旨在将 HTML 内容拆分为可管理的块，同时保留重要元素（如表格、列表和其他 HTML 组件）的语义结构。这确保了此类元素不会被拆分到不同的块中，从而避免丢失上下文相关性，例如表头、列表标题等。
此分割器的核心设计目标是创建具有上下文相关性的块。使用HTMLHeaderTextSplitter进行通用递归分割可能会导致表格、列表和其他结构化元素在中间被切断，从而丢失大量上下文并生成质量较差的块。
HTMLSemanticPreservingSplitter 对于分割包含表格和列表等结构化元素的 HTML 内容至关重要，尤其是当需要保持这些元素完整时。此外，它能够为特定 HTML 标签定义自定义处理程序的能力，使其成为处理复杂 HTML 文档的通用工具。
重要提示: max_chunk_size 并非块（chunk）大小的确定最大值。最大尺寸的计算发生在保留内容不属于该块时，以确保其不会被拆分。当我们将保留数据重新添加回块中时，块的尺寸可能会超过 max_chunk_size。这对于确保维持原始文档的结构至关重要。
信息
笔记:
- 我们已定义一个自定义处理器，用于重新格式化代码块的内容
- 我们为特定的 HTML 元素定义了一个拒绝列表，以便在预处理阶段分解它们及其内容
- \n我们特意设置了较小的块大小，以演示元素不会被拆分
# BeautifulSoup is required to use the custom handlers
from bs4 import Tag
from langchain_text_splitters import HTMLSemanticPreservingSplitter
headers_to_split_on = [
("h1", "Header 1"),
("h2", "Header 2"),
]
def code_handler(element: Tag) -> str:
data_lang = element.get("data-lang")
code_format = f"<code:{data_lang}>{element.get_text()}</code>"
return code_format
splitter = HTMLSemanticPreservingSplitter(
headers_to_split_on=headers_to_split_on,
separators=["\n\n", "\n", ". ", "! ", "? "],
max_chunk_size=50,
preserve_images=True,
preserve_videos=True,
elements_to_preserve=["table", "ul", "ol", "code"],
denylist_tags=["script", "style", "head"],
custom_handlers={"code": code_handler},
)
documents = splitter.split_text(html_string)
documents
API 参考:HTML语义保留分割器
[Document(metadata={'Header 1': 'Main Title'}, page_content='This is an introductory paragraph with some basic content.'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content='This section introduces the topic'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content='. Below is a list: First item Second item Third item with bold text and a link Subsection 1.1: Details This subsection provides additional details'),
Document(metadata={'Header 2': 'Section 1: Introduction'}, page_content=". Here's a table: Header 1 Header 2 Header 3 Row 1, Cell 1 Row 1, Cell 2 Row 1, Cell 3 Row 2, Cell 1 Row 2, Cell 2 Row 2, Cell 3"),
Document(metadata={'Header 2': 'Section 2: Media Content'}, page_content='This section contains an image and a video:  '),
Document(metadata={'Header 2': 'Section 3: Code Example'}, page_content='This section contains a code block: <code:html> <div> <p>This is a paragraph inside a div.</p> </div> </code>'),
Document(metadata={'Header 2': 'Conclusion'}, page_content='This is the conclusion of the document.')]
保留表格和列表
在此示例中，我们将演示 HTMLSemanticPreservingSplitter 如何在 HTML 文档中保留表格和大型列表。块大小将设置为 50 个字符，以说明分割器如何确保这些元素不会被拆分，即使它们超过了定义的最大块大小。
from langchain_text_splitters import HTMLSemanticPreservingSplitter
html_string = """
<!DOCTYPE html>
<html>
<body>
<div>
<h1>Section 1</h1>
<p>This section contains an important table and list that should not be split across chunks.</p>
<table>
<tr>
<th>Item</th>
<th>Quantity</th>
<th>Price</th>
</tr>
<tr>
<td>Apples</td>
<td>10</td>
<td>$1.00</td>
</tr>
<tr>
<td>Oranges</td>
<td>5</td>
<td>$0.50</td>
</tr>
<tr>
<td>Bananas</td>
<td>50</td>
<td>$1.50</td>
</tr>
</table>
<h2>Subsection 1.1</h2>
<p>Additional text in subsection 1.1 that is separated from the table and list.</p>
<p>Here is a detailed list:</p>
<ul>
<li>Item 1: Description of item 1, which is quite detailed and important.</li>
<li>Item 2: Description of item 2, which also contains significant information.</li>
<li>Item 3: Description of item 3, another item that we don't want to split across chunks.</li>
</ul>
</div>
</body>
</html>
"""
headers_to_split_on = [("h1", "Header 1"), ("h2", "Header 2")]
splitter = HTMLSemanticPreservingSplitter(
headers_to_split_on=headers_to_split_on,
max_chunk_size=50,
elements_to_preserve=["table", "ul"],
)
documents = splitter.split_text(html_string)
print(documents)
API 参考:HTML语义保留分割器
[Document(metadata={'Header 1': 'Section 1'}, page_content='This section contains an important table and list'), Document(metadata={'Header 1': 'Section 1'}, page_content='that should not be split across chunks.'), Document(metadata={'Header 1': 'Section 1'}, page_content='Item Quantity Price Apples 10 $1.00 Oranges 5 $0.50 Bananas 50 $1.50'), Document(metadata={'Header 2': 'Subsection 1.1'}, page_content='Additional text in subsection 1.1 that is'), Document(metadata={'Header 2': 'Subsection 1.1'}, page_content='separated from the table and list. Here is a'), Document(metadata={'Header 2': 'Subsection 1.1'}, page_content="detailed list: Item 1: Description of item 1, which is quite detailed and important. Item 2: Description of item 2, which also contains significant information. Item 3: Description of item 3, another item that we don't want to split across chunks.")]
解释
在此示例中，HTMLSemanticPreservingSplitter 确保整个表格和无序列表（<ul>）在各自的块中被完整保留。尽管块大小设置为 50 个字符，但分割器识别出这些元素不应被拆分，因此保持其完整性。
这在处理数据表或列表时尤为重要，因为拆分内容可能导致上下文丢失或混淆。生成的 Document 对象保留了这些元素的完整结构，确保信息的上下文相关性得以维持。
使用自定义处理器
HTMLSemanticPreservingSplitter 允许您为特定的 HTML 元素定义自定义处理程序。某些平台拥有 BeautifulSoup 原生无法解析的自定义 HTML 标签，此时您可以利用自定义处理程序轻松添加格式化逻辑。
这对于需要特殊处理的元素特别有用，例如 <iframe> 标签或特定的 'data-' 元素。在本例中，我们将为 iframe 标签创建一个自定义处理器，将其转换为类似 Markdown 的链接。
def custom_iframe_extractor(iframe_tag):
iframe_src = iframe_tag.get("src", "")
return f"[iframe:{iframe_src}]({iframe_src})"
splitter = HTMLSemanticPreservingSplitter(
headers_to_split_on=headers_to_split_on,
max_chunk_size=50,
separators=["\n\n", "\n", ". "],
elements_to_preserve=["table", "ul", "ol"],
custom_handlers={"iframe": custom_iframe_extractor},
)
html_string = """
<!DOCTYPE html>
<html>
<body>
<div>
<h1>Section with Iframe</h1>
<iframe src="https://example.com/embed"></iframe>
<p>Some text after the iframe.</p>
<ul>
<li>Item 1: Description of item 1, which is quite detailed and important.</li>
<li>Item 2: Description of item 2, which also contains significant information.</li>
<li>Item 3: Description of item 3, another item that we don't want to split across chunks.</li>
</ul>
</div>
</body>
</html>
"""
documents = splitter.split_text(html_string)
print(documents)
[Document(metadata={'Header 1': 'Section with Iframe'}, page_content='[iframe:https://example.com/embed](https://example.com/embed) Some text after the iframe'), Document(metadata={'Header 1': 'Section with Iframe'}, page_content=". Item 1: Description of item 1, which is quite detailed and important. Item 2: Description of item 2, which also contains significant information. Item 3: Description of item 3, another item that we don't want to split across chunks.")]
解释
在此示例中，我们定义了一个自定义处理器用于处理 iframe 标签，将其转换为类 Markdown 格式的链接。当分割器处理 HTML 内容时，它会使用此自定义处理器来转换 iframe 标签，同时保留表格和列表等其他元素。生成的 Document 对象展示了 iframe 如何根据您提供的自定义逻辑进行处理。
重要提示: 在保留链接等项时，您应注意不要在分隔符中包含 .，也不要留空分隔符。RecursiveCharacterTextSplitter 会按句号分割，从而将链接切断。请确保提供包含 . 的分隔符列表。
使用自定义处理器利用 LLM 分析图像
通过自定义处理器，我们还可以覆盖任何元素的默认处理逻辑。一个很好的例子是在分块流程中直接插入对文档内图像进行语义分析。
由于我们的函数在发现标签时会被调用，因此我们可以覆盖 <img> 标签并关闭 preserve_images，以便将我们希望在分块中嵌入的任何内容插入其中。
"""This example assumes you have helper methods `load_image_from_url` and an LLM agent `llm` that can process image data."""
from langchain.agents import AgentExecutor
# This example needs to be replaced with your own agent
llm = AgentExecutor(...)
# This method is a placeholder for loading image data from a URL and is not implemented here
def load_image_from_url(image_url: str) -> bytes:
# Assuming this method fetches the image data from the URL
return b"image_data"
html_string = """
<!DOCTYPE html>
<html>
<body>
<div>
<h1>Section with Image and Link</h1>
<p>
<img src="https://example.com/image.jpg" alt="An example image" />
Some text after the image.
</p>
<ul>
<li>Item 1: Description of item 1, which is quite detailed and important.</li>
<li>Item 2: Description of item 2, which also contains significant information.</li>
<li>Item 3: Description of item 3, another item that we don't want to split across chunks.</li>
</ul>
</div>
</body>
</html>
"""
def custom_image_handler(img_tag) -> str:
img_src = img_tag.get("src", "")
img_alt = img_tag.get("alt", "No alt text provided")
image_data = load_image_from_url(img_src)
semantic_meaning = llm.invoke(image_data)
markdown_text = f"[Image Alt Text: {img_alt} | Image Source: {img_src} | Image Semantic Meaning: {semantic_meaning}]"
return markdown_text
splitter = HTMLSemanticPreservingSplitter(
headers_to_split_on=headers_to_split_on,
max_chunk_size=50,
separators=["\n\n", "\n", ". "],
elements_to_preserve=["ul"],
preserve_images=False,
custom_handlers={"img": custom_image_handler},
)
documents = splitter.split_text(html_string)
print(documents)
API 参考:代理执行器
[Document(metadata={'Header 1': 'Section with Image and Link'}, page_content='[Image Alt Text: An example image | Image Source: https://example.com/image.jpg | Image Semantic Meaning: semantic-meaning] Some text after the image'),
Document(metadata={'Header 1': 'Section with Image and Link'}, page_content=". Item 1: Description of item 1, which is quite detailed and important. Item 2: Description of item 2, which also contains significant information. Item 3: Description of item 3, another item that we don't want to split across chunks.")]
解释：
使用我们编写的自定义处理器从 HTML 的 <img> 元素中提取特定字段，我们可以进一步使用我们的代理处理数据，并将结果直接插入到我们的块中。重要的是要确保将 preserve_images 设置为 False，否则将执行对 <img> 字段的默认处理。