# readthedocs
*author: junjie.jiang*
< br / >
## Desription
To get the list of documents for a single Read the Docs project.
< br / >
## Code Example
### Example
```python
from towhee import DataLoader, pipe, ops
p = (
pipe.input('url')
.map('url', 'text', ops.text_loader())
.flat_map('text', 'sentence', ops.text_splitter())
.map('sentence', 'embedding', ops.sentence_embedding.transformers(model_name='all-MiniLM-L6-v2'))
.map('embedding', 'embedding', ops.towhee.np_normalize())
.output('embedding')
)
for data in DataLoader(ops.data_source.readthedocs('https://towhee.readthedocs.io/en/latest/', include='html', exclude='index.html')):
print(p(data).to_list(kv_format=True))
# batch
for data in DataLoader(ops.data_source.readthedocs('https://towhee.readthedocs.io/en/latest/', include='html', exclude='index.html'), batch_size=10):
p.batch(data)
```
**Parameters:**
***page_prefix:*** *str*
The root path of the page. Generally, the crawled links are relative paths. The complete URL needs to be obtained by splicing the root path + relative path.
***index_page:*** *str*
The main page contains links to all other pages, if None, will use `page_prefix` .
example: https://towhee.readthedocs.io/en/latest/
***include:*** *Union[List[str], str]*
Only contains URLs that meet this condition.
***exclude:*** *Union[List[str], str]*
Filter out URLs that meet this condition.
