Mastodon

Mastodon 是一个去中心化的社交媒体和社交网络服务。

这个加载器从一组Mastodon账户的"toots"中获取文本，使用了Mastodon.py Python包。

公共账号可以默认查询而无需任何认证。如果查询非公开账号或实例，则您需要为您的账户注册一个应用程序以获得访问令牌，并设置该令牌和您的账户的API基础URL。

然后你需要以@account@instance格式输入你想要提取的Mastodon账号名称。

from langchain_community.document_loaders import MastodonTootsLoader

API 参考:MastodonTootsLoader

%pip install --upgrade --quiet  Mastodon.py

loader = MastodonTootsLoader(
    mastodon_accounts=["@Gargron@mastodon.social"],
    number_toots=50,  # Default value is 100
)

# Or set up access information to use a Mastodon app.
# Note that the access token can either be passed into
# constructor or you can set the environment "MASTODON_ACCESS_TOKEN".
# loader = MastodonTootsLoader(
#     access_token="<ACCESS TOKEN OF MASTODON APP>",
#     api_base_url="<API BASE URL OF MASTODON APP INSTANCE>",
#     mastodon_accounts=["@Gargron@mastodon.social"],
#     number_toots=50,  # Default value is 100
# )

documents = loader.load()
for doc in documents[:3]:
    print(doc.page_content)
    print("=" * 80)

<p>It is tough to leave this behind and go back to reality. And some people live here! I’m sure there are downsides but it sounds pretty good to me right now.</p>
================================================================================
<p>I wish we could stay here a little longer, but it is time to go home 🥲</p>
================================================================================
<p>Last day of the honeymoon. And it’s <a href="https://mastodon.social/tags/caturday" class="mention hashtag" rel="tag">#<span>caturday</span></a>! This cute tabby came to the restaurant to beg for food and got some chicken.</p>
================================================================================

默认情况下，toot 文本（文档的 page_content）是 Mastodon API 返回的 HTML 格式。

文档加载器概念指南
文档加载器使用指南

相关​

相关