File size: 5,414 Bytes
7b7cab6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
from langchain_community.document_loaders  import (CSVLoader, WikipediaLoader, UnstructuredURLLoader,
                                        YoutubeLoader, PyPDFLoader, BSHTMLLoader,
                                        Docx2txtLoader, UnstructuredMarkdownLoader)

from langchain_unstructured import UnstructuredLoader


class DocumentLoader:
    def load_unstructured(self, path):
        """
        Load data from a file at the specified path:

        supported files:
        "csv", "doc", "docx", "epub", "image", "md", "msg", "odt", "org", "pdf", "ppt", "pptx", "rtf", "rst", "tsv", "xlsx"


        Args:
            path (str): The file paths

        Returns:
            The loaded  data.

        Exceptions:
            Prints an error message if the loading fails.
        """
        try:
            loader = UnstructuredLoader(path)
            data = loader.load()
            return data
        except Exception as e:
            print(f"Error loading Unstructured: {e}")

    def load_csv(self, path):
        """
        Load data from a CSV file at the specified path.

        Args:
            path (str): The file path to the CSV file.

        Returns:
            The loaded CSV data.

        Exceptions:
            Prints an error message if the CSV loading fails.
        """
        try:
            loader = CSVLoader(file_path=path)
            data = loader.load()
            return data
        except Exception as e:
            print(f"Error loading CSV: {e}")

    def wikipedia_query(self, search_query):
        """
        Query Wikipedia using a given search term and return the results.

        Args:
            search_query (str): The search term to query on Wikipedia.

        Returns:
            The query results.

        Exceptions:
            Prints an error message if the Wikipedia query fails.
        """
        try:
            data = WikipediaLoader(query=search_query, load_max_docs=2).load()
            return data
        except Exception as e:
            print(f"Error querying Wikipedia: {e}")

    def load_urls(self, urls):
        """
        Load and parse content from a list of URLs.

        Args:
            urls (list): A list of URLs to load.

        Returns:
            The loaded data from the URLs.

        Exceptions:
            Prints an error message if loading URLs fails.
        """
        try:
            loader = UnstructuredURLLoader(urls=urls)
            data = loader.load()
            return data
        except Exception as e:
            print(f"Error loading URLs: {e}")

    def load_YouTubeVideo(self, urls):
        """
        Load YouTube video information from provided URLs.

        Args:
            urls (list): A list of YouTube video URLs.

        Returns:
            The loaded documents from the YouTube URLs.

        Exceptions:
            Prints an error message if loading YouTube videos fails.
        """
        try:
            loader = YoutubeLoader.from_youtube_url(
                urls, add_video_info=True, language=["en", "pt", "zh-Hans", "es", "ur", "hi"],
                translation="en")
            documents = loader.load()
            return documents
        except Exception as e:
            print(f"Error loading YouTube video: {e}")

    def load_pdf(self, path):
        """
        Load data from a PDF file at the specified path.

        Args:
            path (str): The file path to the PDF file.

        Returns:
            The loaded and split PDF pages.

        Exceptions:
            Prints an error message if the PDF loading fails.
        """
        try:
            loader = PyPDFLoader(path)
            pages = loader.load_and_split()
            return pages
        except Exception as e:
            print(f"Error loading PDF: {e}")

    def load_text_from_html(self, path):
        """
        Load and parse text content from an HTML file at the specified path.

        Args:
            path (str): The file path to the HTML file.

        Returns:
            The loaded HTML data.

        Exceptions:
            Prints an error message if loading text from HTML fails.
        """
        try:
            loader = BSHTMLLoader(path)
            data = loader.load()
            return data
        except Exception as e:
            print(f"Error loading text from HTML: {e}")

    def load_markdown(self, path):
        """
        Load data from a Markdown file at the specified path.

        Args:
            path (str): The file path to the Markdown file.

        Returns:
            The loaded Markdown data.

        Exceptions:
            Prints an error message if loading Markdown fails.
        """
        try:
            loader = UnstructuredMarkdownLoader(path)
            data = loader.load()
            return data
        except Exception as e:
            print(f"Error loading Markdown: {e}")

    def load_doc(self, path):
        """
        Load data from a DOCX file at the specified path.

        Args:
            path (str): The file path to the DOCX file.

        Returns:
            The loaded DOCX data.

        Exceptions:
            Prints an error message if loading DOCX fails.
        """
        try:
            loader = Docx2txtLoader(path)
            data = loader.load()
            return data
        except Exception as e:
            print(f"Error loading DOCX: {e}")