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
use { crate::{ converter, models::{Chapter, Details, Language, Rating, State, Story}, query::{Document, Element}, select, utils::{req, word_count}, Error, ScrapeError, Uri, }, chrono::{DateTime, NaiveDate, Utc}, std::{fmt::Write, sync::Arc}, }; const NAME: &str = "archive of our own"; const MULTIPLE_CHAPTER_NAME: &str = r#"#chapters > .chapter > div[role="complementary"] > h3"#; const SINGLE_CHAPTER_NAME: &str = r#"#workskin > .preface > .title"#; const CHAPTER_SINGLE: &str = r#"#chapters .userstuff > p"#; const CHAPTER_MULTI_START: &str = r#"#chapters > #chapter-"#; const CHAPTER_MULTI_END: &str = r#" .userstuff > p"#; const STORY_AUTHOR: &str = r#"#workskin > .preface > .byline.heading > a[rel="author"]"#; const STORY_SUMMARY: &str = "#workskin > .preface > .summary > blockquote"; const STORY_NAME: &str = "#workskin > .preface > .title"; const STORY_RATING: &str = ".work > .rating.tags > ul > li > .tag"; const STORY_ORIGINS: &str = ".work > .fandom.tags > ul > li > .tag"; const STORY_STATS_CHAPTERS: &str = "dl.work > dd.stats > dl.stats > dd.chapters"; const STORY_STATS_LANGUAGE: &str = "dl.work > dd.language"; const STORY_STATS_CREATED: &str = "dl.work > dd.stats > dl.stats > dd.published"; const STORY_STATS_UPDATED: &str = "dl.work > dd.stats > dl.stats > dd.status"; 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 url = format!( "https://archiveofourown.org/works/{}?view_full_work=true", id ) .parse::<Uri>()?; let body = req(&url).await?; let html = Arc::new(body); let details = tokio::task::spawn_blocking({ let html = html.clone(); || get_details(html) }) .await .expect("Thread pool closed")?; let chapters = details.chapters; let mut story = Story::new(details); tracing::info!("[{}] Beginning chapter scraping", url); for chapter_number in 1..=chapters { let chapter = tokio::task::spawn_blocking({ let html = html.clone(); move || get_chapter(html, chapter_number) }) .await .expect("Thread pool closed")?; story.chapters.push(chapter); } story.words = story.chapters.iter().map(|c| word_count(&c.main)).sum(); Ok(story) } pub fn get_details(html: impl Into<Document>) -> Result<Details, ScrapeError> { let html = html.into(); let authors: Vec<String> = select!(string[] <> NAME; html => STORY_AUTHOR)?; let origins: Vec<String> = select!(string[] <> NAME; html => STORY_ORIGINS)?; let name: String = select!(string <> NAME; html => STORY_NAME)? .trim() .to_string(); let summary: String = converter::parse(select!(inner_html <> NAME; html => STORY_SUMMARY)?)?; let chapter_expected: String = select!(string <> NAME; html => STORY_STATS_CHAPTERS)?; let chapters: u32 = chapter_expected .split('/') .next() .and_then(|s| s.parse::<u32>().ok()) .unwrap(); let language: Language = match select!(string <> NAME; html => STORY_STATS_LANGUAGE)?.trim() { "English" => Language::English, _ => unreachable!(), }; let rating: Rating = match select!(string <> NAME; html => STORY_RATING)?.trim() { "Explicit" => Rating::Explicit, "Mature" => Rating::Mature, "Teen And Up Audiences" => Rating::Teen, "General Audiences" => Rating::General, _ => unreachable!(), }; let state = { let mut split = chapter_expected.split('/'); let current: &str = split.next().unwrap(); let expected: &str = split.next().unwrap(); if current == expected { State::Completed } else { State::InProgress } }; let created: Option<DateTime<Utc>> = NaiveDate::parse_from_str( &select!(string <> NAME; html => STORY_STATS_CREATED)?, "%Y-%m-%d", ) .map(|date| date.and_hms(0, 0, 0)) .map(|dt| DateTime::from_utc(dt, Utc)) .ok(); let updated: Option<DateTime<Utc>> = if state != State::Completed || chapters != 1 { NaiveDate::parse_from_str( &select!(string <> NAME; html => STORY_STATS_UPDATED)?, "%Y-%m-%d", ) .map(|date| date.and_hms(0, 0, 0)) .map(|dt| DateTime::from_utc(dt, Utc)) .ok() } else if created.is_some() { created } else { None }; Ok(Details { name, summary, chapters, language, rating, state, authors, origins, tags: Vec::new(), created: created.ok_or_else(|| ScrapeError::UnparsableDate(NAME))?, updated: updated.ok_or_else(|| ScrapeError::UnparsableDate(NAME))?, }) } pub fn get_chapter(html: impl Into<Document>, chapter: u32) -> Result<Chapter, ScrapeError> { let html = html.into(); let multi = html.select(format!("{}{}{}", CHAPTER_MULTI_START, chapter, CHAPTER_MULTI_END)); let elements: Vec<Element> = if multi.is_empty() { html.select(CHAPTER_SINGLE) } else { multi }; let content = converter::parse( elements .into_iter() .map(|n| n.html()) .fold(Some(String::new()), |mut buffer, html| { if let Some(mut buff) = buffer.take() { if let Some(raw) = html { write!(buff, "{}", raw).unwrap(); buffer = Some(buff); } } buffer }) .expect("[chapter_text] HTML is missing the chapter text node, did the html change?"), )? .trim() .replace('“', "\"") .replace('”', "\""); let name: String = select!(string <> NAME; html => MULTIPLE_CHAPTER_NAME) .or_else(|_| select!(string <> NAME; html => SINGLE_CHAPTER_NAME)) .map(|title| { let mut title = title.trim().to_string(); if title.starts_with(':') { title.remove(0); title.trim().to_string() } else { title } })?; Ok(Chapter { name, words: word_count(&content), pre: String::new(), post: String::new(), main: content, }) }