Struct extrablatt::extrablatt::Extrablatt

pub struct Extrablatt<TExtractor: Extractor = DefaultExtractor> { /* fields omitted */ }

Caches article downloads

Implementations

impl Extrablatt<DefaultExtractor>

pub fn builder<T: IntoUrl>(url: T) -> Result<ExtrablattBuilder>

Convenience method for creating a new ExtrablattBuilder.

Same as calling ExtrablattBuilder::new.

impl<TExtractor: Extractor> Extrablatt<TExtractor>

pub fn language(&self) -> &Language

pub fn config(&self) -> &Config

The used to store and detect valid articles.

pub fn config_mut(&mut self) -> &mut Config

pub fn extractor(&self) -> &TExtractor

The extractor used to retrieve content for an article.

pub fn categories(&self) -> &FnvHashMap<Category, DocumentDownloadState>

All available categories.

pub fn articles(&self) -> &FnvHashMap<ArticleUrl, DocumentDownloadState>

All available articles.

pub fn clear(&mut self)

Clear all cached articles and categories.

pub async fn download_articles<'_, '_>(
    &'_ mut self
) -> ArticleDownloadIter<'_, TExtractor>

Download and store all outstanding articles and returns an iterator over their results.

Example

Loop over all downloaded articles.

    let mut site = Extrablatt::builder("https://cnn.com/")?.build().await?;
    site.download_all_remaining_categories().await;
    for(url, content) in site.download_articles().await.successes() {
        // ...
    }

pub fn iter_articles(&self) -> ArticleDownloadIter<'_, TExtractor>

Iterator over all known articles.

pub async fn download_category<'_, '_>(
    &'_ mut self,
    category: Category
) -> Result<&'_ Document, ExtrablattError>

Add a category to the pool and downloads it's content.

If the category is already available it's content is only requested if it hasn't been requested or a previous request failed.

pub async fn retry_download_categories<'_>(
    &'_ mut self
) -> Vec<Result<Category, (Category, ExtrablattError)>>

Retry downloading all missing category documents, including failed previous attempts.

pub async fn download_all_remaining_categories<'_>(
    &'_ mut self
) -> Vec<Result<Category, (Category, ExtrablattError)>>

Download and store all categories and their identified articles that haven't been requested yet.

pub async fn refresh_homepage<'_>(
    &'_ mut self
) -> Result<Document, ExtrablattError>

Refresh the main page, insert new categories and return the old document.

impl<TExtractor: Extractor + Unpin> Extrablatt<TExtractor>

pub fn into_stream(self) -> impl Stream<Item = Result<Article, ExtrablattError>>

Converts the newspaper into a stream, yielding all available crate::Articles.

Trait Implementations

impl<TExtractor: Debug + Extractor> Debug for Extrablatt<TExtractor>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.