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
//! Inspired by the Python library "BeautifulSoup," `soup` is a layer on top of //! `html5ever` that aims to provide a slightly different API for querying & //! manipulating HTML //! //! # Examples (inspired by bs4's docs) //! //! Here is the HTML document we will be using for the rest of the examples: //! //! ``` //! const THREE_SISTERS: &'static str = r#" //! <html><head><title>The Dormouse's story</title></head> //! <body> //! <p class="title"><b>The Dormouse's story</b></p> //! //! <p class="story">Once upon a time there were three little sisters; and their names were //! <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>, //! <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and //! <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; //! and they lived at the bottom of a well.</p> //! //! <p class="story">...</p> //! "#; //! # fn main() {} //! ``` //! //! First let's try searching for a tag with a specific name: //! //! ``` //! # extern crate soup; //! # const THREE_SISTERS: &'static str = r#" //! # <html><head><title>The Dormouse's story</title></head> //! # <body> //! # <p class="title"><b>The Dormouse's story</b></p> //! # //! # <p class="story">Once upon a time there were three little sisters; and their names were //! # <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>, //! # <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and //! # <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; //! # and they lived at the bottom of a well.</p> //! # //! # <p class="story">...</p> //! # "#; //! # fn main() { //! use soup::prelude::*; //! //! let soup = Soup::new(THREE_SISTERS); //! //! let title = soup.tag("title").find().expect("Couldn't find tag 'title'"); //! assert_eq!(title.display(), "<title>The Dormouse's story</title>"); //! assert_eq!(title.name(), "title"); //! assert_eq!(title.text(), "The Dormouse's story".to_string()); //! assert_eq!(title.parent().expect("Couldn't find parent of 'title'").name(), "head"); //! //! let p = soup.tag("p").find().expect("Couldn't find tag 'p'"); //! assert_eq!( //! p.display(), //! r#"<p class="title"><b>The Dormouse's story</b></p>"# //! ); //! assert_eq!(p.get("class"), Some("title".to_string())); //! # } //! ``` //! //! So we see that `.find` will give us the first element that matches the query, and we've seen some //! of the methods that we can call on the results. But what if we want to retrieve more than one //! element with the query? For that, we'll use `.find_all`: //! //! ``` //! # extern crate soup; //! # use soup::prelude::*; //! # const THREE_SISTERS: &'static str = r#" //! # <html><head><title>The Dormouse's story</title></head> //! # <body> //! # <p class="title"><b>The Dormouse's story</b></p> //! # //! # <p class="story">Once upon a time there were three little sisters; and their names were //! # <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>, //! # <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and //! # <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; //! # and they lived at the bottom of a well.</p> //! # //! # <p class="story">...</p> //! # "#; //! # fn main() { //! # let soup = Soup::new(THREE_SISTERS); //! // .find returns only the first 'a' tag //! let a = soup.tag("a").find().expect("Couldn't find tag 'a'"); //! assert_eq!( //! a.display(), //! r#"<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>"# //! ); //! // but .find_all will return _all_ of them: //! let a_s = soup.tag("a").find_all(); //! assert_eq!( //! a_s.map(|a| a.display()) //! .collect::<Vec<_>>() //! .join("\n"), //! r#"<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a> //! <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a> //! <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>"# //! ); //! # } //! ``` //! //! Since `.find_all` returns an iterator, you can use it with all the methods you would //! use with other iterators: //! //! ``` //! # extern crate soup; //! # use soup::prelude::*; //! # const THREE_SISTERS: &'static str = r#" //! # <html><head><title>The Dormouse's story</title></head> //! # <body> //! # <p class="title"><b>The Dormouse's story</b></p> //! # //! # <p class="story">Once upon a time there were three little sisters; and their names were //! # <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>, //! # <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and //! # <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; //! # and they lived at the bottom of a well.</p> //! # //! # <p class="story">...</p> //! # "#; //! # fn main() { //! # let soup = Soup::new(THREE_SISTERS); //! let expected = [ //! "http://example.com/elsie", //! "http://example.com/lacie", //! "http://example.com/tillie", //! ]; //! //! for (i, link) in soup.tag("a").find_all().enumerate() { //! let href = link.get("href").expect("Couldn't find link with 'href' attribute"); //! assert_eq!(href, expected[i].to_string()); //! } //! # } //! ``` //! //! The top-level structure we've been working with here, `soup`, implements the same methods //! that the query results do, so you can call the same methods on it and it will delegate the //! calls to the root node: //! //! ``` //! # extern crate soup; //! # use soup::prelude::*; //! # const THREE_SISTERS: &'static str = r#" //! # <html><head><title>The Dormouse's story</title></head> //! # <body> //! # <p class="title"><b>The Dormouse's story</b></p> //! # //! # <p class="story">Once upon a time there were three little sisters; and their names were //! # <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>, //! # <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and //! # <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; //! # and they lived at the bottom of a well.</p> //! # //! # <p class="story">...</p> //! # "#; //! # fn main() { //! # let soup = Soup::new(THREE_SISTERS); //! let text = soup.text(); //! assert_eq!( //! text, //! r#"The Dormouse's story //! //! The Dormouse's story //! //! Once upon a time there were three little sisters; and their names were //! Elsie, //! Lacie and //! Tillie; //! and they lived at the bottom of a well. //! //! ... //! "# //! ); //! # } //! ``` //! //! You can use more than just strings to search for results, such as Regex: //! //! ```rust //! # extern crate regex; //! # extern crate soup; //! # use soup::prelude::*; //! # use std::error::Error; //! use regex::Regex; //! # fn main() -> Result<(), Box<Error>> { //! //! let soup = Soup::new(r#"<body><p>some text, <b>Some bold text</b></p></body>"#); //! let results = soup.tag(Regex::new("^b")?) //! .find_all() //! .map(|tag| tag.name().to_string()) //! .collect::<Vec<_>>(); //! assert_eq!(results, vec!["body".to_string(), "b".to_string()]); //! # Ok(()) //! # } //! ``` //! //! Passing `true` will match everything: //! //! ```rust //! # extern crate soup; //! # use soup::prelude::*; //! # use std::error::Error; //! # fn main() -> Result<(), Box<Error>> { //! //! let soup = Soup::new(r#"<body><p>some text, <b>Some bold text</b></p></body>"#); //! let results = soup.tag(true) //! .find_all() //! .map(|tag| tag.name().to_string()) //! .collect::<Vec<_>>(); //! assert_eq!(results, vec![ //! "html".to_string(), //! "head".to_string(), //! "body".to_string(), //! "p".to_string(), //! "b".to_string(), //! ]); //! # Ok(()) //! # } //! ``` //! //! (also, passing `false` will always return no results, though if that is useful to you, please let me know) //! //! So what can you do once you get the result of a query? Well, for one thing, you can traverse the tree a few //! different ways. You can ascend the tree: //! //! ```rust //! # extern crate soup; //! # use soup::prelude::*; //! # use std::error::Error; //! # fn main() -> Result<(), Box<Error>> { //! //! let soup = Soup::new(r#"<body><p>some text, <b>Some bold text</b></p></body>"#); //! let b = soup.tag("b") //! .find() //! .expect("Couldn't find tag 'b'"); //! let p = b.parent() //! .expect("Couldn't find parent of 'b'"); //! assert_eq!(p.name(), "p".to_string()); //! let body = p.parent() //! .expect("Couldn't find parent of 'p'"); //! assert_eq!(body.name(), "body".to_string()); //! # Ok(()) //! # } //! ``` //! //! Or you can descend it: //! //! ```rust //! # extern crate soup; //! # use soup::prelude::*; //! # use std::error::Error; //! # fn main() -> Result<(), Box<Error>> { //! //! let soup = Soup::new(r#"<body><ul><li>ONE</li><li>TWO</li><li>THREE</li></ul></body>"#); //! let ul = soup.tag("ul") //! .find() //! .expect("Couldn't find tag 'ul'"); //! let mut li_tags = ul.children().filter(|child| child.is_element()); //! assert_eq!(li_tags.next().map(|tag| tag.text().to_string()), Some("ONE".to_string())); //! assert_eq!(li_tags.next().map(|tag| tag.text().to_string()), Some("TWO".to_string())); //! assert_eq!(li_tags.next().map(|tag| tag.text().to_string()), Some("THREE".to_string())); //! assert!(li_tags.next().is_none()); //! # Ok(()) //! # } //! ``` //! //! Or ascend it with an iterator: //! //! ```rust //! # extern crate soup; //! # use soup::prelude::*; //! # use std::error::Error; //! # fn main() -> Result<(), Box<Error>> { //! //! let soup = Soup::new(r#"<body><ul><li>ONE</li><li>TWO</li><li>THREE</li></ul></body>"#); //! let li = soup.tag("li").find().expect("Couldn't find tag 'li'"); //! let mut parents = li.parents(); //! assert_eq!(parents.next().map(|tag| tag.name().to_string()), Some("ul".to_string())); //! assert_eq!(parents.next().map(|tag| tag.name().to_string()), Some("body".to_string())); //! assert_eq!(parents.next().map(|tag| tag.name().to_string()), Some("html".to_string())); //! assert_eq!(parents.next().map(|tag| tag.name().to_string()), Some("[document]".to_string())); //! # Ok(()) //! # } //! ``` #![deny( missing_docs, missing_debug_implementations, missing_copy_implementations, trivial_casts, trivial_numeric_casts, unsafe_code, unstable_features, unused_import_braces, unused_qualifications, rust_2018_compatibility, rust_2018_idioms )] extern crate html5ever; #[cfg(feature = "regex")] extern crate regex; use html5ever::{ parse_document, rcdom::RcDom, tendril::TendrilSink, }; use std::{ fmt, io::{self, Read}, }; /// This module exports all the important types & traits to use `soup` /// effectively pub mod prelude { pub use crate::{node_ext::NodeExt, qb_ext::QueryBuilderExt, Soup}; } pub use crate::{find::QueryBuilder, node_ext::NodeExt, qb_ext::QueryBuilderExt}; mod attribute; mod find; mod qb_ext; mod node_ext; pub mod pattern; /// Parses HTML & provides methods to query & manipulate the document pub struct Soup { handle: RcDom, } impl Soup { /// Create a new `Soup` instance from a string slice /// /// # Example /// /// ```rust /// # extern crate soup; /// # use soup::prelude::*; /// # use std::error::Error; /// # fn main() -> Result<(), Box<Error>> { /// let html = r#" /// <!doctype html> /// <html> /// <head> /// <title>page title</title> /// </head> /// <body> /// <h1>Heading</h1> /// <p>Some text</p> /// <p>Some more text</p> /// </body> /// </html> /// "#; /// /// let soup = Soup::new(html); /// # Ok(()) /// # } /// ``` pub fn new(html: &str) -> Soup { let dom = parse_document(RcDom::default(), Default::default()) .from_utf8() .one(html.as_bytes()); Soup { handle: dom, } } /// Create a new `Soup` instance from something that implements `Read` /// /// This is good for parsing the output of an HTTP response, for example. /// /// ```rust,no_run /// # extern crate reqwest; /// # extern crate soup; /// # use std::error::Error; /// use soup::prelude::*; /// /// # fn main() -> Result<(), Box<Error>> { /// let response = reqwest::get("https://docs.rs/soup")?; /// let soup = Soup::from_reader(response)?; /// # Ok(()) /// # } /// ``` pub fn from_reader<R: Read>(mut reader: R) -> io::Result<Soup> { let dom = parse_document(RcDom::default(), Default::default()) .from_utf8() .read_from(&mut reader)?; Ok(Soup { handle: dom, }) } /// Extracts all text from the HTML pub fn text(&self) -> String { self.handle.document.text() } } impl From<RcDom> for Soup { fn from(rc: RcDom) -> Soup { Soup { handle: rc } } } impl fmt::Debug for Soup { fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { write!(f, "{}", self.handle.document.text()) } } #[cfg(test)] mod tests { use super::*; const TEST_HTML_STRING: &'static str = r#" <!doctype html> <html> <head> <title>foo</title> </head> <body> <p>One</p> <p>Two</p> </body> </html> "#; #[test] fn find() { let soup = Soup::new(TEST_HTML_STRING); let result = soup.tag("p").find().expect("Couldn't find tag 'p'"); assert_eq!(result.text(), "One".to_string()); } #[test] fn find_all() { let soup = Soup::new(TEST_HTML_STRING); let result = soup .tag("p") .find_all() .map(|p| p.text()) .collect::<Vec<_>>(); assert_eq!(result, vec!["One".to_string(), "Two".to_string()]); } }