List of all items
Structs
- contact::Address
- contact::ContactInfo
- contact::Coordinates
- contact::Email
- contact::Phone
- contact::SocialLink
- content::OutlineItem
- extractor::ExtractedLink
- extractor::ExtractorConfig
- extractor::LinkExtractor
- feeds::Feed
- feeds::FeedInfo
- feeds::Sitemap
- fingerprint::AmpInfo
- fingerprint::CacheHints
- fingerprint::ContentFingerprint
- forms::Form
- forms::FormField
- forms::SelectOption
- html::Article
- links::LinkStats
- pagination::PageUrl
- pagination::Pagination
- parser::HtmlParser
- rules::UrlRule
- selector::BOILERPLATE_SELECTORS
- selector::CachedSelectors
- selector::SELECTORS
- types::AlternateLink
- types::CodeBlock
- types::Heading
- types::Image
- types::Link
- types::ListContent
- types::ListItem
- types::OpenGraph
- types::PageMetadata
- types::ParseStats
- types::ParsedContent
- types::ParserConfig
- types::Quote
- types::RobotsMeta
- types::StructuredData
- types::TableCell
- types::TableContent
- types::TableRow
- types::TextContent
- types::TwitterCard
Enums
- contact::EmailSource
- contact::PhoneType
- contact::SocialPlatform
- feeds::FeedType
- feeds::SitemapSource
- feeds::SitemapType
- forms::FieldType
- forms::FormMethod
- forms::FormType
- html::LinkSelectorType
- pagination::PaginationType
- types::ImageLoading
- types::LinkRel
- types::LinkType
- types::ListType
- types::ParserError
- types::StructuredDataFormat
Functions
- contact::detect_phone_type
- contact::detect_social_platform
- contact::extract_address_components
- contact::extract_addresses
- contact::extract_business_name
- contact::extract_contact_info
- contact::extract_email_label
- contact::extract_emails
- contact::extract_phone_label
- contact::extract_phones
- contact::extract_social_links
- contact::extract_social_username
- contact::extract_structured_address
- contact::find_contact_page
- contact::get_emails
- contact::get_phones
- contact::get_social_links
- contact::has_contact_info
- contact::is_valid_email
- content::build_outline
- content::extract_code_block
- content::extract_code_blocks
- content::extract_definition_list
- content::extract_headings
- content::extract_image
- content::extract_images
- content::extract_list
- content::extract_list_item
- content::extract_lists
- content::extract_paragraphs
- content::extract_quotes
- content::extract_table
- content::extract_table_cell
- content::extract_table_row
- content::extract_tables
- content::get_main_heading
- content::is_known_language
- content::resolve_image_url
- feeds::detect_feed_type
- feeds::detect_feed_type_from_url
- feeds::detect_sitemap_type
- feeds::extract_feed_info
- feeds::extract_link_feeds
- feeds::extract_sitemaps
- feeds::generate_feed_urls
- feeds::generate_sitemap_urls
- feeds::get_atom_feed
- feeds::get_feed
- feeds::get_rss_feed
- feeds::get_sitemap
- feeds::has_feeds
- feeds::resolve_url
- fingerprint::content_similarity
- fingerprint::count_elements
- fingerprint::count_text_nodes
- fingerprint::detect_amp_runtime
- fingerprint::detect_amp_version
- fingerprint::detect_is_amp_page
- fingerprint::extract_amp_components
- fingerprint::extract_amp_info
- fingerprint::extract_amp_link
- fingerprint::extract_cache_hints
- fingerprint::extract_canonical_link
- fingerprint::extract_main_content
- fingerprint::extract_structure
- fingerprint::extract_text_only
- fingerprint::fingerprint_document
- fingerprint::generate_fingerprint
- fingerprint::get_amp_url
- fingerprint::has_content_changed
- fingerprint::hash_string
- fingerprint::is_amp_page
- fingerprint::quick_hash
- fingerprint::quick_html_hash
- fingerprint::resolve_url
- forms::associate_labels
- forms::detect_captcha
- forms::detect_csrf_token
- forms::detect_form_type
- forms::extract_form
- forms::extract_form_fields
- forms::extract_forms
- forms::extract_input_field
- forms::extract_select_field
- forms::extract_submit_text
- forms::extract_textarea_field
- forms::get_contact_forms
- forms::get_login_forms
- forms::get_search_forms
- forms::has_forms
- forms::has_login_form
- forms::has_search_form
- html::extract_absolute_links
- html::extract_article
- html::extract_attributes
- html::extract_content
- html::extract_content_by_selector
- html::extract_links
- html::extract_links_by_selector
- html::extract_links_by_xpath
- html::extract_readable_content
- html::extract_texts
- html::resolve_url
- html::sanitize_for_xpath
- html::try_extract_links
- links::calculate_link_stats
- links::determine_link_type
- links::extract_link
- links::extract_links
- links::filter_external_links
- links::filter_followable_links
- links::filter_internal_links
- links::get_external_domains
- links::is_nofollow
- links::is_sponsored
- links::is_ugc
- links::normalize_url
- links::parse_rel_attribute
- links::resolve_url
- metadata::extract_all_og_properties
- metadata::extract_all_twitter_properties
- metadata::extract_alternates
- metadata::extract_apple_touch_icon
- metadata::extract_base_url
- metadata::extract_canonical
- metadata::extract_charset
- metadata::extract_custom_meta
- metadata::extract_favicon
- metadata::extract_json_ld
- metadata::extract_keywords
- metadata::extract_language
- metadata::extract_meta_content
- metadata::extract_metadata
- metadata::extract_microdata
- metadata::extract_og_property
- metadata::extract_opengraph
- metadata::extract_robots
- metadata::extract_structured_data
- metadata::extract_title
- metadata::extract_twitter_card
- metadata::extract_twitter_property
- pagination::detect_infinite_scroll
- pagination::detect_load_more
- pagination::determine_pagination_type
- pagination::extract_page_info_from_text
- pagination::extract_page_links
- pagination::extract_page_number_from_url
- pagination::extract_pagination
- pagination::extract_rel_links
- pagination::generate_page_url
- pagination::get_next_page
- pagination::get_prev_page
- pagination::has_pagination
- pagination::resolve_url
- parser::get_links
- parser::get_metadata
- parser::get_text
- parser::parse
- parser::parse_with_url
- selector::attr_contains_selector
- selector::attr_selector
- selector::attr_starts_with_selector
- selector::child_selector
- selector::class_selector
- selector::descendant_selector
- selector::get_or_create_selector
- selector::heading_selector
- selector::id_selector
- selector::link_rel_selector
- selector::meta_name_selector
- selector::meta_property_selector
- selector::multi_selector
- selector::parse_selector
- selector::try_parse_selector
- text::count_sentences
- text::count_words
- text::detect_language
- text::extract_element_text
- text::extract_text
- text::extract_text_recursive
- text::flesch_kincaid_grade
- text::flesch_reading_ease
- text::is_block_element
- text::is_inline_element
- text::normalize_text
- text::should_skip_element
- text::should_skip_element_by_tag
- text::strip_html_tags
- types::clean_text
- types::normalize_whitespace
- types::truncate_text