0 Fork 0

mirror of https://github.com/langchain-ai/langchain.git synced 2026-10-11 20:35:14 +03:00

Files

T

Leonid Ganeline 59204a5033 docs: document_loaders improvements (#4200 )

- made notebooks consistent: titles, service/format descriptions.
- corrected short names to full names, for example, `Word` -> `Microsoft
Word`
- added missed descriptions
- renamed notebook files to make ToC correctly sorted

2023-05-05 17:44:54 -07:00

2.7 KiB

Raw Blame History

IMSDb

IMSDb is the Internet Movie Script Database.

This covers how to load IMSDb webpages into a document format that we can use downstream.

In [1]:

from langchain.document_loaders import IMSDbLoader

In [2]:

loader = IMSDbLoader("https://imsdb.com/scripts/BlacKkKlansman.html")

In [3]:

data = loader.load()

In [8]:

data[0].page_content[:500]

Out [8]:

'\n\r\n\r\n\r\n\r\n                                    BLACKKKLANSMAN\r\n                         \r\n                         \r\n                         \r\n                         \r\n                                      Written by\r\n\r\n                          Charlie Wachtel & David Rabinowitz\r\n\r\n                                         and\r\n\r\n                              Kevin Willmott & Spike Lee\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n                         FADE IN:\r\n                         \r\n          SCENE FROM "GONE WITH'

In [6]:

data[0].metadata

Out [6]:

{'source': 'https://imsdb.com/scripts/BlacKkKlansman.html'}

2.7 KiB Raw Blame History

IMSDb

2.7 KiB

Raw Blame History