langchain/docs/extras/modules/data_connection/document_loaders/integrations/imsdb.ipynb

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'}