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
use { crate::{ converter, models::{Chapter, Details, Language, Rating, State, Story}, query::Document, select, utils::{req, sleep, word_count}, Error, ScrapeError, Uri, }, chrono::{TimeZone, Utc}, std::str, }; const NAME: &str = "fanfiction"; const CHAPTER_NAME: &str = "select#chap_select > option[selected]"; const CHAPTER_TEXT: &str = "#storytext"; const STORY_AUTHOR: &str = "#profile_top > a.xcontrast_txt"; const STORY_DETAILS: &str = "#profile_top > span.xgray.xcontrast_txt"; const STORY_DETAILS_RATING: &str = r#"#profile_top > span.xgray.xcontrast_txt > a[target="rating"]"#; const STORY_DETAILS_DATES: &str = "#profile_top > span.xgray.xcontrast_txt > span[data-xutime]"; const STORY_SUMMARY: &str = "#profile_top > div.xcontrast_txt"; const STORY_NAME: &str = "#profile_top > b.xcontrast_txt"; const STORY_ORIGINS: &str = "#pre_story_links > span.lc-left > a.xcontrast_txt"; pub async fn scrape(url: &Uri) -> Result<Story, Error> { let id = url .path() .split('/') .filter(|s| !s.is_empty()) .nth(1) .expect("No story ID found in URL"); tracing::info!("[{}] Scraping initial details", url); let body = req(&url).await?; let details = tokio::task::spawn_blocking(|| get_details(body)) .await .expect("Thread pool closed")?; let chapters = details.chapters; let mut story = Story::new(details); tracing::info!("[{}] Beginning chapter scraping", url); if chapters != 1 { for page in 1..=chapters { tracing::info!("[{}] Scraping chapter {}", url, page); sleep().await?; let url = format!("https://www.fanfiction.net/s/{}/{}", id, page) .as_str() .parse()?; let body = req(&url).await?; story.chapters.push( tokio::task::spawn_blocking(|| get_chapter(body)) .await .expect("Thread pool closed")?, ); } } else { tracing::info!("[{}] Scraping chapter {}", url, 1); sleep().await?; let url = format!("https://www.fanfiction.net/s/{}/{}", id, 1) .as_str() .parse()?; let body = req(&url).await?; story.chapters.push( tokio::task::spawn_blocking(|| get_chapter(body)) .await .expect("Thread pool closed")?, ); } story.words = story.chapters.iter().map(|c| word_count(&c.main)).sum(); Ok(story) } pub fn get_details(body: impl Into<Document>) -> Result<Details, ScrapeError> { let html = body.into(); let name: String = select!(string <> NAME; html => STORY_NAME)?; let summary: String = select!(string <> NAME; html => STORY_SUMMARY)?; let details: String = select!(string <> NAME; html => STORY_DETAILS)?; let author: String = html .select(STORY_AUTHOR) .into_iter() .next() .map(|ele| ele.text()) .flatten() .ok_or(crate::error::ScrapeError::ElementNotFound( NAME, &STORY_AUTHOR, ))?; let origins: Vec<String> = html .select(STORY_ORIGINS) .into_iter() .last() .map(|ele| { ele.text() .map(|mut text| { if text.ends_with("Crossover") { let len = text.len(); let new_len = len.saturating_sub("Crossover".len()); text.truncate(new_len); } text }) .map(|text| { text.split(" + ") .map(str::trim) .filter(|s| !s.is_empty()) .map(String::from) .collect::<Vec<String>>() }) }) .flatten() .ok_or(crate::error::ScrapeError::ElementNotFound( NAME, &STORY_ORIGINS, ))?; let mut chapters = 1u32; let mut language = Language::English; let rating = match select!(string <> NAME; html => STORY_DETAILS_RATING)? .as_str() .split(' ') .map(str::trim) .filter(|s| !s.is_empty()) .nth(1) { Some("MA") => Rating::Explicit, Some("M") => Rating::Mature, Some("T") => Rating::Teen, Some("K") | Some("K+") => Rating::General, rating => unreachable!("Unknown rating found, please report this: {:?}", rating), }; let mut state = State::InProgress; let (created, mut updated) = match html.select(STORY_DETAILS_DATES).as_slice() { [first] => { let published = first .attr("data-xutime") .ok_or_else(|| ScrapeError::AttributeNotFound(NAME, "data-xutime"))?; (Utc.datetime_from_str(&published, "%s").ok(), None) } [first, second] => { let updated = first .attr("data-xutime") .ok_or_else(|| ScrapeError::AttributeNotFound(NAME, "data-xutime"))?; let published = second .attr("data-xutime") .ok_or_else(|| ScrapeError::AttributeNotFound(NAME, "data-xutime"))?; ( Utc.datetime_from_str(&published, "%s").ok(), Utc.datetime_from_str(&updated, "%s").ok(), ) } _ => { return Err(ScrapeError::UnparsableDate(NAME)); } }; let words = details.split('-').count(); for (i, s) in details.split('-').map(str::trim).rev().enumerate() { if s.starts_with("Chapters: ") { if let Some(ch) = s .split(':') .map(str::trim) .nth(1) .and_then(|s| s.parse::<u32>().ok()) { chapters = ch; } } if i == words - 2 { language = match s { "English" => Language::English, _ => unreachable!(), }; } if s.starts_with("Status: ") { if let Some(st) = s.split(':').map(str::trim).nth(1).map(|s| match s { "Complete" => State::Completed, _ => unreachable!(), }) { state = st; } } } if updated.is_none() && created.is_some() { updated = created; } Ok(Details { name, summary, chapters, language, rating, state, authors: vec![author], origins, tags: Vec::new(), created: created.ok_or_else(|| ScrapeError::UnparsableDate(NAME))?, updated: updated.ok_or_else(|| ScrapeError::UnparsableDate(NAME))?, }) } pub fn get_chapter(body: impl Into<Document>) -> Result<Chapter, ScrapeError> { let html = body.into(); let mut main = converter::parse( html.select(CHAPTER_TEXT) .first() .and_then(|node| node.inner_html()) .expect("[chapter_text] HTML is missing the chapter text node, did the html change?"), )?; while main.ends_with(' ') { let len = main.len(); let new_len = len.saturating_sub(" ".len()); main.truncate(new_len); } Ok(Chapter { name: html .select(CHAPTER_NAME) .first() .and_then(|cn| cn.text()) .map(|cn| cn.split(' ').skip(1).collect::<Vec<_>>().join(" ")) .or_else(|| { Some( select!(string <> NAME; html => STORY_NAME).expect( "[chapter_name] Unable to use story title as fallback chapter title", ), ) }) .expect("[chapter_name] No text in selected element"), words: word_count(&main), pre: String::new(), post: String::new(), main, }) }