AttributeError: 'CrawlResult' object has no attribute 'fit_markdown'

[wg20170107]

trafficstars

import asyncio from crawl4ai import AsyncWebCrawler import json

async def main(): async with AsyncWebCrawler(verbos=True) as crawler: result = await crawler.arun( url="https://batteriesnews.com/lg-chem-files-lawsuit-against-unit-of-chinas-ronbay-over-battery-tech", bypass_cache=True, word_count_threshold=10, ) print(result.fit_markdown) # Print clean markdown content

AttributeError: 'CrawlResult' object has no attribute 'fit_markdown' result.markdown no problem

[unclecode]

@wg20170107 Make sure to update your library (current version 0.3.72). If not, reinstall it with pip using 'pip install -U cralw4ai', as it already includes the added feature, which should be the only reason.

[tonyOgbonna]

`import asyncio from crawl4ai import AsyncWebCrawler import json

async def main(): async with AsyncWebCrawler(verbos=True) as crawler: result = await crawler.arun( url="https://www.accenture.com/us-en/insights/song/generative-ai-customer-growth", word_count_threshold=10, )
print(result.fit_markdown) # Print clean markdown content

if name == "main": asyncio.run(main())`

OUTPUT: [INIT].... → Crawl4AI 0.4.247 [FETCH]... ↓ https://www.accenture.com/us-en/insights/song/gene... | Status: True | Time: 0.01s [COMPLETE] ● https://www.accenture.com/us-en/insights/song/gene... | Status: True | Total: 0.01s None

result.markdown no problem

[unclecode]

Hi @tonyOgbonna Please check documentation, now we are at version 0.4.247, certain things has changed, specially markdown.

[ekeric13]

i am also getting this issue. crawl4ai>=0.5.0.post8. this is from the source code

class CrawlerRunConfig():
    def __init__(
        self,
        # Content Processing Parameters
        word_count_threshold: int = MIN_WORD_THRESHOLD,
        extraction_strategy: ExtractionStrategy = None,
        chunking_strategy: ChunkingStrategy = RegexChunking(),
        markdown_generator: MarkdownGenerationStrategy = None,
        only_text: bool = False,
        css_selector: str = None,
        target_elements: List[str] = None,
        excluded_tags: list = None,
        excluded_selector: str = None,
        keep_data_attributes: bool = False,
        keep_attrs: list = None,
        remove_forms: bool = False,
        prettiify: bool = False,
        parser_type: str = "lxml",
        scraping_strategy: ContentScrapingStrategy = None,
        proxy_config: Union[ProxyConfig, dict, None] = None,
        proxy_rotation_strategy: Optional[ProxyRotationStrategy] = None,
        # SSL Parameters
        fetch_ssl_certificate: bool = False,
        # Caching Parameters
        cache_mode: CacheMode = CacheMode.BYPASS,
        session_id: str = None,
        bypass_cache: bool = False,
        disable_cache: bool = False,
        no_cache_read: bool = False,
        no_cache_write: bool = False,
        shared_data: dict = None,
        # Page Navigation and Timing Parameters
        wait_until: str = "domcontentloaded",
        page_timeout: int = PAGE_TIMEOUT,
        wait_for: str = None,
        wait_for_images: bool = False,
        delay_before_return_html: float = 0.1,
        mean_delay: float = 0.1,
        max_range: float = 0.3,
        semaphore_count: int = 5,
        # Page Interaction Parameters
        js_code: Union[str, List[str]] = None,
        js_only: bool = False,
        ignore_body_visibility: bool = True,
        scan_full_page: bool = False,
        scroll_delay: float = 0.2,
        process_iframes: bool = False,
        remove_overlay_elements: bool = False,
        simulate_user: bool = False,
        override_navigator: bool = False,
        magic: bool = False,
        adjust_viewport_to_content: bool = False,
        # Media Handling Parameters
        screenshot: bool = False,
        screenshot_wait_for: float = None,
        screenshot_height_threshold: int = SCREENSHOT_HEIGHT_TRESHOLD,
        pdf: bool = False,
        image_description_min_word_threshold: int = IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
        image_score_threshold: int = IMAGE_SCORE_THRESHOLD,
        table_score_threshold: int = 7,
        exclude_external_images: bool = False,
        # Link and Domain Handling Parameters
        exclude_social_media_domains: list = None,
        exclude_external_links: bool = False,
        exclude_social_media_links: bool = False,
        exclude_domains: list = None,
        exclude_internal_links: bool = False,
        # Debugging and Logging Parameters
        verbose: bool = True,
        log_console: bool = False,
        # Connection Parameters
        method: str = "GET",
        stream: bool = False,
        url: str = None,
        check_robots_txt: bool = False,
        user_agent: str = None,
        user_agent_mode: str = None,
        user_agent_generator_config: dict = {},
        # Deep Crawl Parameters
        deep_crawl_strategy: Optional[DeepCrawlStrategy] = None,
        # Experimental Parameters
        experimental: Dict[str, Any] = None,
    ):

as you can see it is literally not an option to be passed in but literally the 2nd code snippet in the docs push me to use this option so i am confused on whether it is deprecated or i am messing up https://docs.crawl4ai.com/core/simple-crawling/

[kn-cbre]

@ekeric13 did you happen to find any solution for this ?