Spaces:
Runtime error
Runtime error
File size: 5,798 Bytes
ed13a16 019b332 15fc415 0502a8f 15fc415 4402168 15fc415 9a4cf94 5962cca ed13a16 c170de8 ed13a16 5962cca 15fc415 c170de8 15fc415 9a4cf94 15fc415 dbe5b53 15fc415 c170de8 15fc415 c170de8 9a4cf94 c170de8 15fc415 9a4cf94 dbe5b53 15fc415 9a4cf94 15fc415 9a4cf94 15fc415 5962cca 9a4cf94 5962cca 4460730 9a4cf94 5962cca 9a4cf94 15fc415 f94ac50 15fc415 f94ac50 15fc415 f94ac50 15fc415 f94ac50 15fc415 f94ac50 15fc415 |
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 |
//! The `duckduckgo` module handles the scraping of results from the duckduckgo search engine
//! by querying the upstream duckduckgo search engine with user provided query and with a page
//! number if provided.
use std::{collections::HashMap, time::Duration};
use reqwest::header::{HeaderMap, CONTENT_TYPE, COOKIE, REFERER, USER_AGENT};
use scraper::{Html, Selector};
use crate::results::aggregation_models::RawSearchResult;
use super::engine_models::EngineError;
use error_stack::{IntoReport, Report, Result, ResultExt};
/// This function scrapes results from the upstream engine duckduckgo and puts all the scraped
/// results like title, visiting_url (href in html),engine (from which engine it was fetched from)
/// and description in a RawSearchResult and then adds that to HashMap whose keys are url and
/// values are RawSearchResult struct and then returns it within a Result enum.
///
/// # Arguments
///
/// * `query` - Takes the user provided query to query to the upstream search engine with.
/// * `page` - Takes an u32 as an argument.
/// * `user_agent` - Takes a random user agent string as an argument.
///
/// # Errors
///
/// Returns an `EngineErrorKind` if the user is not connected to the internet or if their is failure to
/// reach the above `upstream search engine` page or if the `upstream search engine` is unable to
/// provide results for the requested search query and also returns error if the scraping selector
/// or HeaderMap fails to initialize.
pub async fn results(
query: &str,
page: u32,
user_agent: &str,
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
// Page number can be missing or empty string and so appropriate handling is required
// so that upstream server receives valid page number.
let url: String = match page {
1 => {
format!("https://html.duckduckgo.com/html/?q={query}&s=&dc=&v=1&o=json&api=/d.js")
}
_ => {
format!(
"https://duckduckgo.com/html/?q={}&s={}&dc={}&v=1&o=json&api=/d.js",
query,
(page / 2 + (page % 2)) * 30,
(page / 2 + (page % 2)) * 30 + 1
)
}
};
// initializing HeaderMap and adding appropriate headers.
let mut header_map = HeaderMap::new();
header_map.insert(
USER_AGENT,
user_agent
.parse()
.into_report()
.change_context(EngineError::UnexpectedError)?,
);
header_map.insert(
REFERER,
"https://google.com/"
.parse()
.into_report()
.change_context(EngineError::UnexpectedError)?,
);
header_map.insert(
CONTENT_TYPE,
"application/x-www-form-urlencoded"
.parse()
.into_report()
.change_context(EngineError::UnexpectedError)?,
);
header_map.insert(
COOKIE,
"kl=wt-wt"
.parse()
.into_report()
.change_context(EngineError::UnexpectedError)?,
);
// fetch the html from upstream duckduckgo engine
let results: String = reqwest::Client::new()
.get(url)
.timeout(Duration::from_secs(5))
.headers(header_map) // add spoofed headers to emulate human behavior
.send()
.await
.into_report()
.change_context(EngineError::RequestError)?
.text()
.await
.into_report()
.change_context(EngineError::RequestError)?;
let document: Html = Html::parse_document(&results);
let no_result: Selector = Selector::parse(".no-results")
.map_err(|_| Report::new(EngineError::UnexpectedError))
.attach_printable_lazy(|| format!("invalid CSS selector: {}", ".no-results"))?;
if document.select(&no_result).next().is_some() {
return Err(Report::new(EngineError::EmptyResultSet));
}
let results: Selector = Selector::parse(".result")
.map_err(|_| Report::new(EngineError::UnexpectedError))
.attach_printable_lazy(|| format!("invalid CSS selector: {}", ".result"))?;
let result_title: Selector = Selector::parse(".result__a")
.map_err(|_| Report::new(EngineError::UnexpectedError))
.attach_printable_lazy(|| format!("invalid CSS selector: {}", ".result__a"))?;
let result_url: Selector = Selector::parse(".result__url")
.map_err(|_| Report::new(EngineError::UnexpectedError))
.attach_printable_lazy(|| format!("invalid CSS selector: {}", ".result__url"))?;
let result_desc: Selector = Selector::parse(".result__snippet")
.map_err(|_| Report::new(EngineError::UnexpectedError))
.attach_printable_lazy(|| format!("invalid CSS selector: {}", ".result__snippet"))?;
// scrape all the results from the html
Ok(document
.select(&results)
.map(|result| {
RawSearchResult::new(
result
.select(&result_title)
.next()
.unwrap()
.inner_html()
.trim()
.to_string(),
format!(
"https://{}",
result
.select(&result_url)
.next()
.unwrap()
.inner_html()
.trim()
),
result
.select(&result_desc)
.next()
.unwrap()
.inner_html()
.trim()
.to_string(),
vec!["duckduckgo".to_string()],
)
})
.map(|search_result| (search_result.visiting_url.clone(), search_result))
.collect())
}
|