o
    a+ iD                     @   s`   d dl Z d dlZd dlmZmZmZmZ d dlmZ d dl	m
Z
 d dlmZ G dd deZdS )    N)AnyIteratorLiteralOptional)
BaseLoader)Document)get_from_envc                   @   sn   e Zd ZdZ	ddddddddee dee dee dee d	ed
 dee fddZde	e
 fddZdS )FireCrawlLoadera!
  
    FireCrawlLoader document loader integration

    Setup:
        Install ``firecrawl-py``,``langchain_community`` and set environment variable ``FIRECRAWL_API_KEY``.

        .. code-block:: bash

            pip install -U firecrawl-py langchain_community
            export FIRECRAWL_API_KEY="your-api-key"

    Instantiate:
        .. code-block:: python

            from langchain_community.document_loaders import FireCrawlLoader

            loader = FireCrawlLoader(
                url = "https://firecrawl.dev",
                mode = "crawl"
                # other params = ...
            )

    Lazy load:
        .. code-block:: python

            docs = []
            docs_lazy = loader.lazy_load()

            # async variant:
            # docs_lazy = await loader.alazy_load()

            for doc in docs_lazy:
                docs.append(doc)
            print(docs[0].page_content[:100])
            print(docs[0].metadata)

        .. code-block:: python

            Introducing [Smart Crawl!](https://www.firecrawl.dev/smart-crawl)
             Join the waitlist to turn any web
            {'ogUrl': 'https://www.firecrawl.dev/', 'title': 'Home - Firecrawl', 'robots': 'follow, index', 'ogImage': 'https://www.firecrawl.dev/og.png?123', 'ogTitle': 'Firecrawl', 'sitemap': {'lastmod': '2024-08-12T00:28:16.681Z', 'changefreq': 'weekly'}, 'keywords': 'Firecrawl,Markdown,Data,Mendable,Langchain', 'sourceURL': 'https://www.firecrawl.dev/', 'ogSiteName': 'Firecrawl', 'description': 'Firecrawl crawls and converts any website into clean markdown.', 'ogDescription': 'Turn any website into LLM-ready data.', 'pageStatusCode': 200, 'ogLocaleAlternate': []}

    Async load:
        .. code-block:: python

            docs = await loader.aload()
            print(docs[0].page_content[:100])
            print(docs[0].metadata)

        .. code-block:: python

            Introducing [Smart Crawl!](https://www.firecrawl.dev/smart-crawl)
             Join the waitlist to turn any web
            {'ogUrl': 'https://www.firecrawl.dev/', 'title': 'Home - Firecrawl', 'robots': 'follow, index', 'ogImage': 'https://www.firecrawl.dev/og.png?123', 'ogTitle': 'Firecrawl', 'sitemap': {'lastmod': '2024-08-12T00:28:16.681Z', 'changefreq': 'weekly'}, 'keywords': 'Firecrawl,Markdown,Data,Mendable,Langchain', 'sourceURL': 'https://www.firecrawl.dev/', 'ogSiteName': 'Firecrawl', 'description': 'Firecrawl crawls and converts any website into clean markdown.', 'ogDescription': 'Turn any website into LLM-ready data.', 'pageStatusCode': 200, 'ogLocaleAlternate': []}

    Ncrawl)queryapi_keyapi_urlmodeparamsurlr   r   r   r   )r
   scrapemapextractsearchr   c          	      C   s   zddl m} W n ty   tdw |dvr td| d|dv r*|s*td|d	kr;|s;|r7|d
s;td|pAtdd}|pJtdpJd}|||d| _ |pUd| _|| _	|p]i | _
|durj|| j
d
< dS dS )a  Initialize with API key and url.

        Args:
            url: The url to be crawled.
            api_key: The Firecrawl API key. If not specified will be read from env var
                FIRECRAWL_API_KEY. Get an API key
            api_url: The Firecrawl API URL. If not specified will be read from env var
                FIRECRAWL_API_URL or defaults to https://api.firecrawl.dev.
            mode: The mode to run the loader in. Default is "crawl".
                 Options include "scrape" (single url),
                 "crawl" (all accessible sub pages),
                 "map" (returns list of links that are semantically related).
                 "extract" (extracts structured data from a page).
                 "search" (search for data across the web).
            params: The parameters to pass to the Firecrawl API.
                Examples include crawlerOptions.
                For more details, visit: https://github.com/mendableai/firecrawl-py
        r   )FirecrawlAppzD`firecrawl` package not found, please run `pip install firecrawl-py`)r
   r   r   r   r   r   Invalid mode 'zT'.
                Allowed: 'crawl', 'scrape', 'search', 'map', 'extract', 'search'.)r   r
   r   r   z2Url must be provided for modes other than 'search'r   r   z&Query must be provided for search moder   ZFIRECRAWL_API_KEYZFIRECRAWL_API_URLzhttps://api.firecrawl.dev)r   r    N)	firecrawlr   ImportError
ValueErrorgetr   osgetenvr   r   r   )	selfr   r   r   r   r   r   r   Zresolved_api_url r   z/home/app/PaddleOCR-VL-test/.venv_paddleocr/lib/python3.10/site-packages/langchain_community/document_loaders/firecrawl.py__init__F   s2   


zFireCrawlLoader.__init__returnc              	   #   s   g }| j dkr*h d  fdd| j D }d|d< | jj| jfi |g}n| j dkr| js6tdh d	  fd
d| j D }d|d< | jj| jfi |}t|t	rm|
dg }t|trit|ng }nt|dg }t|tr|t|ng }n| j dkr| jstdh d  fdd| j D }d|d< | jj| jfi |}t|t	r|
d}t|trt|ng }nFt|drt|d}t|trt|ng }n/t|t}|rt|ng }n | j dkr| jstdh d  fdd| j D }d|d< t| jj| jgfi |g}n| j dkrh d  fdd| j D }d|d< | jjd4d| j
di|}t|trMt|}ng }	g }
t|t	rf|
d|
d|
dg}
nt|dd t|dd t|dd g}
d|
d fd|
d fd|
d ffD ]s\}}|sq|D ]f}t|t	st|dd n|
d}t|t	st|d d n|
d }t|t	st|d!d n|
d!}|p|p|pd"}d#d ||t|t	st|d$d n|
d$|d% D }|	||d& qq|	}n	td'| j  d(|D ]}| j dkrt|tr|}i }n_t|t	rV|
dp2|
d)p2d"}t|tr;|nt|p@d"}d*d |
d |
d!d+ D }n(t|dsbt|d rt|dd"pnt|d)d"}t|trw|nt|p|d"}i }t|d d }t|d!d }|d ur||d < |d ur||d!< nt|}i }n| j dkrt|}i }n| j dkrt|t	r|
d,pd"}t|tr|nt|pd"}|
d-i }t|t	r|ni }nt|}i }nt|t	r|
d,p|
d.p|
d/d"}t|tr|nt|pd"}|
d-i }n,t|d,d p/t|d.d p/t|d/d"}t|tr8|nt|p=d"}t|d-i pGi }t|t	s~t|d0r_t|jr_| }nt|rkt|}nt|d1rxt	t|}nd2t|i}|sq
t||d3V  q
d S )5Nr   >   Zstore_in_cacheZmax_ageexclude_tagsZmobiletimeoutparsersZskip_tls_verificationZ	block_adsZuse_mocklocationZinclude_tagsproxyZonly_main_contentZremove_base64_imagesactionsheaderswait_forformatsZ	fast_modec                       i | ]\}}| v r||qS r   r   .0kvallowedr   r    
<dictcomp>       z-FireCrawlLoader.lazy_load.<locals>.<dictcomp>Z	langchainZintegrationr
   zURL is required for crawl mode>   limitZcrawl_entire_domainscrape_optionsZmax_concurrencyZzero_data_retentionZinclude_pathsZwebhookZmax_discovery_depthallow_external_linkspromptZallow_subdomainsdelaypoll_intervalr$   Zexclude_pathsZignore_query_parametersZignore_sitemapc                    r,   r   r   r-   r1   r   r    r3      r4   datar   zURL is required for map mode>   r&   r5   Zsitemapr$   r   Zinclude_subdomainsc                    r,   r   r   r-   r1   r   r    r3      r4   linksr   z URL is required for extract mode>   Zschemaignore_invalid_urlsr6   r7   Zshow_sourcesr8   Zsystem_promptZagentr:   r$   Zenable_web_searchc                    r,   r   r   r-   r1   r   r    r3      r4   r   >   r&   r5   
categoriesr=   r6   Ztbsr$   sourcesc                    r,   r   r   r-   r1   r   r    r3      r4   r   ZwebnewsZimagesr         r   titledescriptionr   c                 S      i | ]\}}|d ur||qS Nr   r-   r   r   r    r3   $  s
    	category)r   rC   rG   type)markdownmetadatar   zJ'.
                Allowed: 'crawl', 'scrape', 'map', 'extract', 'search'.hrefc                 S   rE   rF   r   r-   r   r   r    r3   F  s
    )rC   rD   rI   rJ   htmlZrawHtml
model_dump__dict__value)page_contentrJ   r   )r   r   itemsr   r   r   r   r
   
isinstancedictr   listgetattrr   hasattrstrr   r   appendcallablerM   dataclassesis_dataclassasdictvarsr   )r   Zfirecrawl_docskwargsZcrawl_responser;   Zmap_responser<   Zis_listZsearch_dataresults
containerskindrQ   itemZurl_valZ	title_valZdesc_valZcontent_valZmetadata_valdocrP   metaZpage_content_valuerC   rD   Zmarkdown_valueZmetadata_objZcontent_valuer   r1   r    	lazy_load   sn  








 









 



"


zFireCrawlLoader.lazy_loadrF   )__name__
__module____qualname____doc__r   rW   r   rS   r!   r   r   re   r   r   r   r    r	   
   s.    =
;r	   )rZ   r   typingr   r   r   r   Zlangchain_core.document_loadersr   Zlangchain_core.documentsr   Zlangchain_core.utilsr   r	   r   r   r   r    <module>   s    