File size: 3,146 Bytes
cfd3735
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2dfc4698",
   "metadata": {},
   "source": [
    "# HTML\n",
    "\n",
    ">[The HyperText Markup Language or HTML](https://en.wikipedia.org/wiki/HTML) is the standard markup language for documents designed to be displayed in a web browser.\n",
    "\n",
    "This covers how to load `HTML` documents into a document format that we can use downstream."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "24b434b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders import UnstructuredHTMLLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "00f46fda",
   "metadata": {},
   "outputs": [],
   "source": [
    "loader = UnstructuredHTMLLoader(\"example_data/fake-content.html\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b68a26b3",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = loader.load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "34de48fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='My First Heading\\n\\nMy first paragraph.', lookup_str='', metadata={'source': 'example_data/fake-content.html'}, lookup_index=0)]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "00337aae",
   "metadata": {},
   "source": [
    "## Loading HTML with BeautifulSoup4\n",
    "\n",
    "We can also use `BeautifulSoup4` to load HTML documents using the `BSHTMLLoader`.  This will extract the text from the HTML into `page_content`, and the page title as `title` into `metadata`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "79b1bce4",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.document_loaders import BSHTMLLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4be99e6c",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='\\n\\nTest Title\\n\\n\\nMy First Heading\\nMy first paragraph.\\n\\n\\n', metadata={'source': 'example_data/fake-content.html', 'title': 'Test Title'})]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loader = BSHTMLLoader(\"example_data/fake-content.html\")\n",
    "data = loader.load()\n",
    "data"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}