Spaces:
Sleeping
Sleeping
File size: 27,429 Bytes
097eaf0 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 | use std::collections::{HashMap, HashSet};
use std::sync::LazyLock;
use kuchikiki::{iter::NodeEdge, parse_html, traits::TendrilSink, NodeRef};
use napi_derive::napi;
use nodesig::{get_node_signature, SignatureMode};
use regex::Regex;
use serde::{Deserialize, Serialize};
use serde_json::Value;
use tokio::task;
use url::Url;
static URL_REGEX: LazyLock<Regex> =
LazyLock::new(|| Regex::new(r#"url\(['"]?([^'")]+)['"]?\)"#).expect("URL_REGEX is a valid static regex pattern"));
use crate::utils::to_napi_err;
fn _extract_base_href_from_document(
document: &NodeRef,
url: &Url,
) -> Result<String, Box<dyn std::error::Error + Send + Sync>> {
if let Some(base) = document
.select("base[href]")
.map_err(|_| "Failed to select base href".to_string())?
.next()
.and_then(|base| base.attributes.borrow().get("href").map(|x| x.to_string()))
{
if let Ok(base) = url.join(&base) {
return Ok(base.to_string());
}
}
Ok(url.to_string())
}
fn _extract_base_href(
html: &str,
url: &str,
) -> Result<String, Box<dyn std::error::Error + Send + Sync>> {
let document = parse_html().one(html);
let url = Url::parse(url)?;
_extract_base_href_from_document(&document, &url)
}
/// Extract the base href from HTML document.
#[napi]
pub async fn extract_base_href(html: String, url: String) -> napi::Result<String> {
let res = task::spawn_blocking(move || _extract_base_href(&html, &url))
.await
.map_err(|e| {
napi::Error::new(
napi::Status::GenericFailure,
format!("extract_base_href join error: {e}"),
)
})?;
res.map_err(to_napi_err)
}
/// Extract all links from HTML document.
#[napi]
pub async fn extract_links(html: Option<String>) -> napi::Result<Vec<String>> {
task::spawn_blocking(move || {
let html = match html {
Some(h) => h,
None => return Ok(Vec::new()),
};
let document = parse_html().one(html.as_str());
let anchors: Vec<_> = document
.select("a[href]")
.map_err(|_| to_napi_err("Failed to select links"))?
.collect();
let mut out: Vec<String> = Vec::new();
for anchor in anchors {
let mut href = match anchor.attributes.borrow().get("href") {
Some(x) => x.to_string(),
None => continue,
};
if href.starts_with("http:/") && !href.starts_with("http://") {
href = format!("http://{}", &href[6..]);
} else if href.starts_with("https:/") && !href.starts_with("https://") {
href = format!("https://{}", &href[7..]);
}
out.push(href);
}
Ok(out)
})
.await
.map_err(|e| {
napi::Error::new(
napi::Status::GenericFailure,
format!("extract_links join error: {e}"),
)
})?
}
macro_rules! insert_meta_name {
($out:ident, $document:ident, $metaName:expr, $outName:expr) => {
if let Some(x) = $document
.select(&format!("meta[name=\"{}\"]", $metaName))
.map_err(|_| "Failed to select meta name")?
.next()
.and_then(|description| {
description
.attributes
.borrow()
.get("content")
.map(|x| x.to_string())
})
{
$out.insert(($outName).to_string(), Value::String(x));
}
};
}
macro_rules! insert_meta_property {
($out:ident, $document:ident, $metaName:expr, $outName:expr) => {
if let Some(x) = $document
.select(&format!("meta[property=\"{}\"]", $metaName))
.map_err(|_| "Failed to select meta property")?
.next()
.and_then(|description| {
description
.attributes
.borrow()
.get("content")
.map(|x| x.to_string())
})
{
$out.insert(($outName).to_string(), Value::String(x));
}
};
}
fn _extract_metadata(
html: &str,
) -> Result<HashMap<String, Value>, Box<dyn std::error::Error + Send + Sync>> {
let document = parse_html().one(html);
let mut out = HashMap::<String, Value>::new();
let head_node = document
.select("head")
.map_err(|_| "Failed to select head")?
.next();
let search_root = head_node.as_ref().map(|h| h.as_node()).unwrap_or(&document);
if let Some(title) = search_root
.select("title")
.map_err(|_| "Failed to select title")?
.next()
{
out.insert("title".to_string(), Value::String(title.text_contents()));
}
if let Some(favicon_link) = search_root
.select("link[rel=\"icon\"]")
.map_err(|_| "Failed to select favicon")?
.next()
.and_then(|x| x.attributes.borrow().get("href").map(|x| x.to_string()))
.or_else(|| {
search_root
.select("link[rel*=\"icon\"]")
.ok()
.and_then(|mut x| {
x.next()
.and_then(|x| x.attributes.borrow().get("href").map(|x| x.to_string()))
})
})
{
out.insert("favicon".to_string(), Value::String(favicon_link));
}
if let Some(lang) = document
.select("html[lang]")
.map_err(|_| "Failed to select lang")?
.next()
.and_then(|x| x.attributes.borrow().get("lang").map(|x| x.to_string()))
{
out.insert("language".to_string(), Value::String(lang));
}
insert_meta_property!(out, search_root, "og:title", "ogTitle");
insert_meta_property!(out, search_root, "og:description", "ogDescription");
insert_meta_property!(out, search_root, "og:url", "ogUrl");
insert_meta_property!(out, search_root, "og:image", "ogImage");
insert_meta_property!(out, search_root, "og:audio", "ogAudio");
insert_meta_property!(out, search_root, "og:determiner", "ogDeterminer");
insert_meta_property!(out, search_root, "og:locale", "ogLocale");
for meta in search_root
.select("meta[property=\"og:locale:alternate\"]")
.map_err(|_| "Failed to select og locale alternate")?
{
let attrs = meta.attributes.borrow();
if let Some(content) = attrs.get("content") {
if let Some(v) = out.get_mut("ogLocaleAlternate") {
match v {
Value::Array(x) => x.push(Value::String(content.to_string())),
_ => unreachable!(),
}
} else {
out.insert(
"ogLocaleAlternate".to_string(),
Value::Array(vec![Value::String(content.to_string())]),
);
}
}
}
insert_meta_property!(out, document, "og:site_name", "ogSiteName");
insert_meta_property!(out, document, "og:video", "ogVideo");
insert_meta_name!(out, document, "article:section", "articleSection");
insert_meta_name!(out, document, "article:tag", "articleTag");
insert_meta_property!(out, document, "article:published_time", "publishedTime");
insert_meta_property!(out, document, "article:modified_time", "modifiedTime");
insert_meta_name!(out, document, "dcterms.keywords", "dcTermsKeywords");
insert_meta_name!(out, document, "dc.description", "dcDescription");
insert_meta_name!(out, document, "dc.subject", "dcSubject");
insert_meta_name!(out, document, "dcterms.subject", "dcTermsSubject");
insert_meta_name!(out, document, "dcterms.audience", "dcTermsAudience");
insert_meta_name!(out, document, "dc.type", "dcType");
insert_meta_name!(out, document, "dcterms.type", "dcTermsType");
insert_meta_name!(out, document, "dc.date", "dcDate");
insert_meta_name!(out, document, "dc.date.created", "dcDateCreated");
insert_meta_name!(out, document, "dcterms.created", "dcTermsCreated");
for meta in document
.select("meta")
.map_err(|_| "Failed to select meta")?
{
let meta = meta.as_node().as_element().unwrap();
let attrs = meta.attributes.borrow();
if let Some(name) = attrs
.get("name")
.or_else(|| attrs.get("property"))
.or_else(|| attrs.get("itemprop"))
{
if let Some(content) = attrs.get("content") {
if let Some(v) = out.get(name) {
match v {
Value::String(existing) => {
if name == "description" {
out.insert(
name.to_string(),
Value::String(format!("{existing}, {content}")),
);
} else if name != "title" {
out.insert(
name.to_string(),
Value::Array(vec![
Value::String(existing.clone()),
Value::String(content.to_string()),
]),
);
}
}
Value::Array(existing_array) => {
if name == "description" {
let mut values: Vec<String> = existing_array
.iter()
.filter_map(|v| match v {
Value::String(s) => Some(s.clone()),
_ => None,
})
.collect();
values.push(content.to_string());
out.insert(name.to_string(), Value::String(values.join(", ")));
} else {
match out.get_mut(name) {
Some(Value::Array(x)) => x.push(Value::String(content.to_string())),
_ => unreachable!(),
}
}
}
_ => unreachable!(),
}
} else {
out.insert(name.to_string(), Value::String(content.to_string()));
}
}
}
}
// Backfill title from og:title, twitter:title, or meta[name="title"] if primary extraction failed
if !out.contains_key("title") {
let fallback_title = out
.get("ogTitle")
.or_else(|| out.get("og:title"))
.or_else(|| out.get("twitter:title"))
.and_then(|v| match v {
Value::String(s) if !s.is_empty() => Some(s.clone()),
_ => None,
});
if let Some(title) = fallback_title {
out.insert("title".to_string(), Value::String(title));
}
}
Ok(out)
}
/// Extract metadata from HTML document.
#[napi]
pub async fn extract_metadata(html: Option<String>) -> napi::Result<HashMap<String, Value>> {
task::spawn_blocking(move || {
let html = match html {
Some(h) => h,
None => return Ok(HashMap::new()),
};
_extract_metadata(&html).map_err(to_napi_err)
})
.await
.map_err(|e| {
napi::Error::new(
napi::Status::GenericFailure,
format!("extract_metadata join error: {e}"),
)
})?
}
const EXCLUDE_NON_MAIN_TAGS: [&str; 42] = [
"header",
"footer",
"nav",
"aside",
".header",
".top",
".navbar",
"#header",
".footer",
".bottom",
"#footer",
".sidebar",
".side",
".aside",
"#sidebar",
".modal",
".popup",
"#modal",
".overlay",
".ad",
".ads",
".advert",
"#ad",
".lang-selector",
".language",
"#language-selector",
".social",
".social-media",
".social-links",
"#social",
".menu",
".navigation",
"#nav",
".breadcrumbs",
"#breadcrumbs",
".share",
"#share",
".widget",
"#widget",
".cookie",
"#cookie",
".fc-decoration",
];
const FORCE_INCLUDE_MAIN_TAGS: [&str; 13] = [
"#main",
".swoogo-cols",
".swoogo-text",
".swoogo-table-div",
".swoogo-space",
".swoogo-alert",
".swoogo-sponsors",
".swoogo-title",
".swoogo-tabs",
".swoogo-logo",
".swoogo-image",
".swoogo-button",
".swoogo-agenda",
];
#[derive(Deserialize, Serialize)]
#[napi(object)]
pub struct TransformHtmlOptions {
pub html: String,
pub url: String,
#[serde(default)]
pub include_tags: Vec<String>,
#[serde(default)]
pub exclude_tags: Vec<String>,
pub only_main_content: bool,
pub omce_signatures: Option<Vec<String>>,
}
struct ImageSource {
url: String,
size: f64,
is_x: bool,
}
fn _transform_html_inner(
opts: TransformHtmlOptions,
) -> Result<String, Box<dyn std::error::Error + Send + Sync>> {
let mut document = parse_html().one(opts.html.as_ref());
let url = Url::parse(&_extract_base_href_from_document(
&document,
&Url::parse(&opts.url)?,
)?)?;
if !opts.include_tags.is_empty() {
let new_document = parse_html().one("<div></div>");
let root = new_document
.select_first("div")
.map_err(|_| "Failed to select root element")?;
for x in opts.include_tags.iter() {
let matching_nodes: Vec<_> = document
.select(x)
.map_err(|_| "Failed to include_tags tags")?
.collect();
for tag in matching_nodes {
root.as_node().append(tag.as_node().clone());
}
}
document = new_document;
}
while let Ok(x) = document.select_first("head") {
x.as_node().detach();
}
while let Ok(x) = document.select_first("meta") {
x.as_node().detach();
}
while let Ok(x) = document.select_first("noscript") {
x.as_node().detach();
}
while let Ok(x) = document.select_first("style") {
x.as_node().detach();
}
while let Ok(x) = document.select_first("script") {
x.as_node().detach();
}
// OMCE first
if opts.only_main_content {
if let Some(signatures) = opts.omce_signatures.as_ref() {
let mut nodes_to_drop: Vec<NodeRef> = Vec::new();
let modes = signatures
.iter()
.map(|x| Into::<SignatureMode>::into(x.split(':').nth(1).unwrap().to_string()))
.collect::<HashSet<_>>();
for mode in modes {
let matcher = format!(":{}:", Into::<String>::into(mode));
let signatures = signatures
.iter()
.filter(|x| x.contains(&matcher))
.cloned()
.collect::<HashSet<_>>();
for edge in document.traverse() {
match edge {
NodeEdge::Start(_) => {}
NodeEdge::End(node) => {
if node.as_element().is_none() {
continue;
}
if node.text_contents().trim().is_empty() {
continue;
}
let signature = get_node_signature(&node, mode);
if signatures.contains(&signature) {
nodes_to_drop.push(node);
}
}
}
}
}
for node in nodes_to_drop {
node.detach();
}
}
}
for x in opts.exclude_tags.iter() {
while let Ok(x) = document.select_first(x) {
x.as_node().detach();
}
}
if opts.only_main_content {
for x in EXCLUDE_NON_MAIN_TAGS.iter() {
let x: Vec<_> = document
.select(x)
.map_err(|_| "Failed to select tags")?
.collect();
for tag in x {
if !FORCE_INCLUDE_MAIN_TAGS.iter().any(|x| {
tag
.as_node()
.select(x)
.is_ok_and(|mut x| x.next().is_some())
}) {
tag.as_node().detach();
}
}
}
}
let srcset_images: Vec<_> = document
.select("img[srcset]")
.map_err(|_| "Failed to select srcset images")?
.collect();
for img in srcset_images {
let mut sizes: Vec<ImageSource> = img
.attributes
.borrow()
.get("srcset")
.ok_or("Failed to get srcset")?
.split(',')
.filter_map(|x| {
let tok: Vec<&str> = x.trim().split(' ').collect();
let last_token = tok[tok.len() - 1];
let (last_token, last_token_used) = if tok.len() > 1
&& !last_token.is_empty()
&& (last_token.ends_with('x') || last_token.ends_with('w'))
{
(last_token, true)
} else {
("1x", false)
};
if let Some((last_index, _)) = last_token.char_indices().last() {
if let Ok(parsed_size) = last_token[..last_index].parse() {
Some(ImageSource {
url: if last_token_used {
tok[0..tok.len() - 1].join(" ")
} else {
tok.join(" ")
},
size: parsed_size,
is_x: last_token.ends_with('x'),
})
} else {
None
}
} else {
None
}
})
.collect();
if sizes.iter().all(|x| x.is_x) {
if let Some(src) = img.attributes.borrow().get("src").map(|x| x.to_string()) {
sizes.push(ImageSource {
url: src,
size: 1.0,
is_x: true,
});
}
}
sizes.sort_by(|a, b| {
b.size
.partial_cmp(&a.size)
.unwrap_or(std::cmp::Ordering::Equal)
});
if let Some(biggest) = sizes.first() {
img
.attributes
.borrow_mut()
.insert("src", biggest.url.clone());
}
}
let src_images: Vec<_> = document
.select("img[src]")
.map_err(|_| "Failed to select src images")?
.collect();
for img in src_images {
let old = img
.attributes
.borrow()
.get("src")
.map(|x| x.to_string())
.ok_or("Failed to get src")?;
if let Ok(new) = url.join(&old) {
img.attributes.borrow_mut().insert("src", new.to_string());
}
}
let href_anchors: Vec<_> = document
.select("a[href]")
.map_err(|_| "Failed to select href anchors")?
.collect();
for anchor in href_anchors {
let old = anchor
.attributes
.borrow()
.get("href")
.map(|x| x.to_string())
.ok_or("Failed to get href")?;
if let Ok(new) = url.join(&old) {
anchor
.attributes
.borrow_mut()
.insert("href", new.to_string());
}
}
Ok(document.to_string())
}
/// Transform and clean HTML content based on provided options.
#[napi]
pub async fn transform_html(opts: TransformHtmlOptions) -> napi::Result<String> {
let res = task::spawn_blocking(move || _transform_html_inner(opts))
.await
.map_err(|e| {
napi::Error::new(
napi::Status::GenericFailure,
format!("transform_html join error: {e}"),
)
})?;
res.map_err(to_napi_err)
}
fn _get_inner_json(html: &str) -> Result<String, ()> {
Ok(parse_html().one(html).select_first("body")?.text_contents())
}
/// Extract inner text content from HTML body.
#[napi]
pub async fn get_inner_json(html: String) -> napi::Result<String> {
let res = task::spawn_blocking(move || _get_inner_json(&html))
.await
.map_err(|e| {
napi::Error::new(
napi::Status::GenericFailure,
format!("get_inner_json join error: {e}"),
)
})?;
res.map_err(|_| to_napi_err("Failed to get inner JSON"))
}
#[derive(Deserialize, Serialize)]
#[napi(object)]
pub struct AttributeSelector {
pub selector: String,
pub attribute: String,
}
#[derive(Deserialize, Serialize)]
#[napi(object)]
pub struct ExtractAttributesOptions {
pub selectors: Vec<AttributeSelector>,
}
#[derive(Serialize)]
#[napi(object)]
pub struct ExtractedAttributeResult {
pub selector: String,
pub attribute: String,
pub values: Vec<String>,
}
fn _extract_attributes(
html: &str,
options: &ExtractAttributesOptions,
) -> Result<Vec<ExtractedAttributeResult>, Box<dyn std::error::Error + Send + Sync>> {
let document = parse_html().one(html);
let mut results = Vec::new();
for selector_config in &options.selectors {
let mut values = Vec::new();
let elements: Vec<_> = match document.select(&selector_config.selector).map_err(|_| {
format!(
"Failed to select with selector: {}",
selector_config.selector
)
}) {
Ok(x) => x.collect(),
Err(_) => Vec::new(), // invalid selector => empty list
};
for element in elements {
if let Some(attr_value) = element
.attributes
.borrow()
.get(selector_config.attribute.as_str())
{
values.push(attr_value.to_string());
continue;
}
if !selector_config.attribute.starts_with("data-") {
let data_attr = format!("data-{}", selector_config.attribute);
if let Some(attr_value) = element.attributes.borrow().get(data_attr.as_str()) {
values.push(attr_value.to_string());
}
}
}
results.push(ExtractedAttributeResult {
selector: selector_config.selector.clone(),
attribute: selector_config.attribute.clone(),
values,
});
}
Ok(results)
}
/// Extract specified attributes from HTML elements matching selectors.
#[napi]
pub async fn extract_attributes(
html: String,
options: ExtractAttributesOptions,
) -> napi::Result<Vec<ExtractedAttributeResult>> {
let res = task::spawn_blocking(move || _extract_attributes(&html, &options))
.await
.map_err(|e| {
napi::Error::new(
napi::Status::GenericFailure,
format!("extract_attributes join error: {e}"),
)
})?;
res.map_err(to_napi_err)
}
fn _extract_images(
html: &str,
base_url: &str,
) -> Result<Vec<String>, Box<dyn std::error::Error + Send + Sync>> {
let document = parse_html().one(html);
let base_url = Url::parse(base_url)?;
let base_href = _extract_base_href_from_document(&document, &base_url)?;
let base_href_url = Url::parse(&base_href)?;
let mut images = HashSet::<String>::new();
let resolve_image_url = |src: &str| -> Result<String, Box<dyn std::error::Error + Send + Sync>> {
if src.starts_with("data:") || src.starts_with("blob:") {
return Ok(src.to_string());
}
if src.starts_with("http://") || src.starts_with("https://") {
return Ok(src.to_string());
}
if src.starts_with("//") {
let resolved = base_url.join(src)?;
return Ok(resolved.to_string());
}
let resolved = base_href_url.join(src)?;
Ok(resolved.to_string())
};
// <img>
let img_elements: Vec<_> = match document
.select("img")
.map_err(|_| "Failed to select img tags")
{
Ok(x) => x.collect(),
Err(e) => return Err(e.into()),
};
for img in img_elements {
let attrs = img.attributes.borrow();
if let Some(src) = attrs.get("src") {
if let Ok(resolved) = resolve_image_url(src) {
images.insert(resolved);
}
}
if let Some(data_src) = attrs.get("data-src") {
if let Ok(resolved) = resolve_image_url(data_src) {
images.insert(resolved);
}
}
if let Some(srcset) = attrs.get("srcset") {
for part in srcset.split(',') {
if let Some(url) = part.split_whitespace().next() {
if !url.is_empty() {
if let Ok(resolved) = resolve_image_url(url) {
images.insert(resolved);
}
}
}
}
}
}
// <picture><source>
let source_elements: Vec<_> = match document
.select("picture source")
.map_err(|_| "Failed to select picture source")
{
Ok(x) => x.collect(),
Err(_) => Vec::new(),
};
for source in source_elements {
if let Some(srcset) = source.attributes.borrow().get("srcset") {
for part in srcset.split(',') {
if let Some(url) = part.split_whitespace().next() {
if !url.is_empty() {
if let Ok(resolved) = resolve_image_url(url) {
images.insert(resolved);
}
}
}
}
}
}
// OG/Twitter images
let meta_selectors = [
"meta[property=\"og:image\"]",
"meta[property=\"og:image:url\"]",
"meta[property=\"og:image:secure_url\"]",
"meta[name=\"twitter:image\"]",
"meta[name=\"twitter:image:src\"]",
"meta[itemprop=\"image\"]",
];
for selector in &meta_selectors {
if let Ok(elements) = document.select(selector) {
for element in elements {
if let Some(content) = element.attributes.borrow().get("content") {
if let Ok(resolved) = resolve_image_url(content) {
images.insert(resolved);
}
}
}
}
}
// icons
let link_selectors = [
"link[rel*=\"icon\"]",
"link[rel*=\"apple-touch-icon\"]",
"link[rel*=\"image_src\"]",
];
for selector in &link_selectors {
if let Ok(elements) = document.select(selector) {
for element in elements {
if let Some(href) = element.attributes.borrow().get("href") {
if let Ok(resolved) = resolve_image_url(href) {
images.insert(resolved);
}
}
}
}
}
// <video poster="">
if let Ok(video_elements) = document.select("video[poster]") {
for video in video_elements {
if let Some(poster) = video.attributes.borrow().get("poster") {
if let Ok(resolved) = resolve_image_url(poster) {
images.insert(resolved);
}
}
}
}
// <... style="background: url(...)"> or <... style="background-image: url(...)">
if let Ok(elements) = document.select("[style*=\"background\"]") {
for element in elements {
if let Some(style) = element.attributes.borrow().get("style") {
for cap in URL_REGEX.captures_iter(style) {
if let Some(url_match) = cap.get(1) {
let url = url_match.as_str().trim();
if !url.is_empty() {
if let Ok(resolved) = resolve_image_url(url) {
images.insert(resolved);
}
}
}
}
}
}
}
let filtered_images: Vec<String> = images
.into_iter()
.filter(|url| !url.to_lowercase().starts_with("javascript:"))
.filter(|url| !url.is_empty())
.filter(|url| url.starts_with("data:") || url.starts_with("blob:") || Url::parse(url).is_ok())
.collect();
Ok(filtered_images)
}
/// Extract all image URLs from HTML document.
#[napi]
pub async fn extract_images(html: String, base_url: String) -> napi::Result<Vec<String>> {
let res = task::spawn_blocking(move || _extract_images(&html, &base_url))
.await
.map_err(|e| {
napi::Error::new(
napi::Status::GenericFailure,
format!("extract_images join error: {e}"),
)
})?;
res.map_err(to_napi_err)
}
/// Process multi-line links in markdown.
#[napi]
pub async fn post_process_markdown(markdown: String) -> napi::Result<String> {
let res = task::spawn_blocking(move || {
let mut link_open_count = 0usize;
let mut out = String::with_capacity(markdown.len());
for ch in markdown.chars() {
match ch {
'[' => {
link_open_count += 1;
}
']' => {
link_open_count = link_open_count.saturating_sub(1);
}
_ => {}
}
let inside_link_content = link_open_count > 0;
if inside_link_content && ch == '\n' {
out.push('\\');
out.push('\n');
} else {
out.push(ch);
}
}
remove_skip_to_content_links(&out)
})
.await
.map_err(|e| {
napi::Error::new(
napi::Status::GenericFailure,
format!("post_process_markdown join error: {e}"),
)
})?;
Ok(res)
}
fn remove_skip_to_content_links(input: &str) -> String {
const LABEL: &str = "Skip to Content";
let bytes = input.as_bytes();
let len = bytes.len();
let mut out = String::with_capacity(len);
let mut i = 0;
'outer: while i < len {
if bytes[i] == b'[' {
let label_start = i + 1;
let label_end = label_start + LABEL.len();
if label_end <= len && bytes[label_start..label_end].iter().all(|b| b.is_ascii()) {
let label_slice = &input[label_start..label_end];
if label_slice.eq_ignore_ascii_case(LABEL)
&& label_end + 3 <= len
&& bytes[label_end] == b']'
&& bytes[label_end + 1] == b'('
&& bytes[label_end + 2] == b'#'
{
let mut j = label_end + 3;
while j < len {
let ch = input[j..].chars().next().unwrap();
if ch == ')' {
i = j + ch.len_utf8();
continue 'outer;
}
j += ch.len_utf8();
}
}
}
}
let ch = input[i..].chars().next().unwrap();
out.push(ch);
i += ch.len_utf8();
}
out
}
|