Merge branch 'rolling' into patch-searx-results-on-first-page
Browse files- docs/configuration.md +1 -0
- docs/installation.md +1 -0
- src/config/parser.rs +3 -0
- src/engines/duckduckgo.rs +3 -1
- src/engines/engine_models.rs +3 -1
- src/engines/searx.rs +5 -2
- src/results/aggregator.rs +7 -3
- src/server/routes.rs +2 -0
- websurfx/config.lua +1 -0
docs/configuration.md
CHANGED
@@ -29,6 +29,7 @@ Some of the configuration options provided in the file are stated below. These a
|
|
29 |
- **port:** Port number on which server should be launched.
|
30 |
- **binding_ip_addr:** IP address on the which server should be launched.
|
31 |
- **production_use:** Whether to use production mode or not (in other words this option should be used if it is to be used to host it on the server to provide a service to a large number of users). If production_use is set to true. There will be a random delay before sending the request to the search engines, this is to prevent DDoSing the upstream search engines from a large number of simultaneous requests. This is newly added option and hence is only available in the **edge version**.
|
|
|
32 |
|
33 |
## Website
|
34 |
|
|
|
29 |
- **port:** Port number on which server should be launched.
|
30 |
- **binding_ip_addr:** IP address on the which server should be launched.
|
31 |
- **production_use:** Whether to use production mode or not (in other words this option should be used if it is to be used to host it on the server to provide a service to a large number of users). If production_use is set to true. There will be a random delay before sending the request to the search engines, this is to prevent DDoSing the upstream search engines from a large number of simultaneous requests. This is newly added option and hence is only available in the **edge version**.
|
32 |
+
- **request_timeout:** Timeout for the search requests sent to the upstream search engines to be fetched (value in seconds).
|
33 |
|
34 |
## Website
|
35 |
|
docs/installation.md
CHANGED
@@ -86,6 +86,7 @@ binding_ip_addr = "0.0.0.0" --ip address on the which server should be launched.
|
|
86 |
production_use = false -- whether to use production mode or not (in other words this option should be used if it is to be used to host it on the server to provide a service to a large number of users)
|
87 |
-- if production_use is set to true
|
88 |
-- There will be a random delay before sending the request to the search engines, this is to prevent DDoSing the upstream search engines from a large number of simultaneous requests.
|
|
|
89 |
|
90 |
-- ### Website ###
|
91 |
-- The different colorschemes provided are:
|
|
|
86 |
production_use = false -- whether to use production mode or not (in other words this option should be used if it is to be used to host it on the server to provide a service to a large number of users)
|
87 |
-- if production_use is set to true
|
88 |
-- There will be a random delay before sending the request to the search engines, this is to prevent DDoSing the upstream search engines from a large number of simultaneous requests.
|
89 |
+
request_timeout = 60 -- timeout for the search requests sent to the upstream search engines to be fetched (value in seconds).
|
90 |
|
91 |
-- ### Website ###
|
92 |
-- The different colorschemes provided are:
|
src/config/parser.rs
CHANGED
@@ -22,6 +22,7 @@ static CONFIG_FILE_NAME: &str = "config.lua";
|
|
22 |
/// * `logging` - It stores the option to whether enable or disable logs.
|
23 |
/// * `debug` - It stores the option to whether enable or disable debug mode.
|
24 |
/// * `upstream_search_engines` - It stores all the engine names that were enabled by the user.
|
|
|
25 |
#[derive(Clone)]
|
26 |
pub struct Config {
|
27 |
pub port: u16,
|
@@ -32,6 +33,7 @@ pub struct Config {
|
|
32 |
pub logging: bool,
|
33 |
pub debug: bool,
|
34 |
pub upstream_search_engines: Vec<String>,
|
|
|
35 |
}
|
36 |
|
37 |
/// Configuration options for the aggregator.
|
@@ -80,6 +82,7 @@ impl Config {
|
|
80 |
.into_iter()
|
81 |
.filter_map(|(key, value)| value.then_some(key))
|
82 |
.collect(),
|
|
|
83 |
})
|
84 |
})
|
85 |
}
|
|
|
22 |
/// * `logging` - It stores the option to whether enable or disable logs.
|
23 |
/// * `debug` - It stores the option to whether enable or disable debug mode.
|
24 |
/// * `upstream_search_engines` - It stores all the engine names that were enabled by the user.
|
25 |
+
/// * `request_timeout` - It stores the time (secs) which controls the server request timeout.
|
26 |
#[derive(Clone)]
|
27 |
pub struct Config {
|
28 |
pub port: u16,
|
|
|
33 |
pub logging: bool,
|
34 |
pub debug: bool,
|
35 |
pub upstream_search_engines: Vec<String>,
|
36 |
+
pub request_timeout: u8,
|
37 |
}
|
38 |
|
39 |
/// Configuration options for the aggregator.
|
|
|
82 |
.into_iter()
|
83 |
.filter_map(|(key, value)| value.then_some(key))
|
84 |
.collect(),
|
85 |
+
request_timeout: globals.get::<_, u8>("request_timeout")?,
|
86 |
})
|
87 |
})
|
88 |
}
|
src/engines/duckduckgo.rs
CHANGED
@@ -29,6 +29,7 @@ impl SearchEngine for DuckDuckGo {
|
|
29 |
/// * `query` - Takes the user provided query to query to the upstream search engine with.
|
30 |
/// * `page` - Takes an u32 as an argument.
|
31 |
/// * `user_agent` - Takes a random user agent string as an argument.
|
|
|
32 |
///
|
33 |
/// # Errors
|
34 |
///
|
@@ -41,6 +42,7 @@ impl SearchEngine for DuckDuckGo {
|
|
41 |
query: String,
|
42 |
page: u32,
|
43 |
user_agent: String,
|
|
|
44 |
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
|
45 |
// Page number can be missing or empty string and so appropriate handling is required
|
46 |
// so that upstream server recieves valid page number.
|
@@ -90,7 +92,7 @@ impl SearchEngine for DuckDuckGo {
|
|
90 |
);
|
91 |
|
92 |
let document: Html = Html::parse_document(
|
93 |
-
&DuckDuckGo::fetch_html_from_upstream(self, url, header_map).await?,
|
94 |
);
|
95 |
|
96 |
let no_result: Selector = Selector::parse(".no-results")
|
|
|
29 |
/// * `query` - Takes the user provided query to query to the upstream search engine with.
|
30 |
/// * `page` - Takes an u32 as an argument.
|
31 |
/// * `user_agent` - Takes a random user agent string as an argument.
|
32 |
+
/// * `request_timeout` - Takes a time (secs) as a value which controls the server request timeout.
|
33 |
///
|
34 |
/// # Errors
|
35 |
///
|
|
|
42 |
query: String,
|
43 |
page: u32,
|
44 |
user_agent: String,
|
45 |
+
request_timeout: u8,
|
46 |
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
|
47 |
// Page number can be missing or empty string and so appropriate handling is required
|
48 |
// so that upstream server recieves valid page number.
|
|
|
92 |
);
|
93 |
|
94 |
let document: Html = Html::parse_document(
|
95 |
+
&DuckDuckGo::fetch_html_from_upstream(self, url, header_map, request_timeout).await?,
|
96 |
);
|
97 |
|
98 |
let no_result: Selector = Selector::parse(".no-results")
|
src/engines/engine_models.rs
CHANGED
@@ -50,11 +50,12 @@ pub trait SearchEngine {
|
|
50 |
&self,
|
51 |
url: String,
|
52 |
header_map: reqwest::header::HeaderMap,
|
|
|
53 |
) -> Result<String, EngineError> {
|
54 |
// fetch the html from upstream search engine
|
55 |
Ok(reqwest::Client::new()
|
56 |
.get(url)
|
57 |
-
.timeout(Duration::from_secs(
|
58 |
.headers(header_map) // add spoofed headers to emulate human behaviour
|
59 |
.send()
|
60 |
.await
|
@@ -71,5 +72,6 @@ pub trait SearchEngine {
|
|
71 |
query: String,
|
72 |
page: u32,
|
73 |
user_agent: String,
|
|
|
74 |
) -> Result<HashMap<String, RawSearchResult>, EngineError>;
|
75 |
}
|
|
|
50 |
&self,
|
51 |
url: String,
|
52 |
header_map: reqwest::header::HeaderMap,
|
53 |
+
request_timeout: u8,
|
54 |
) -> Result<String, EngineError> {
|
55 |
// fetch the html from upstream search engine
|
56 |
Ok(reqwest::Client::new()
|
57 |
.get(url)
|
58 |
+
.timeout(Duration::from_secs(request_timeout as u64)) // Add timeout to request to avoid DDOSing the server
|
59 |
.headers(header_map) // add spoofed headers to emulate human behaviour
|
60 |
.send()
|
61 |
.await
|
|
|
72 |
query: String,
|
73 |
page: u32,
|
74 |
user_agent: String,
|
75 |
+
request_timeout: u8,
|
76 |
) -> Result<HashMap<String, RawSearchResult>, EngineError>;
|
77 |
}
|
src/engines/searx.rs
CHANGED
@@ -27,6 +27,7 @@ impl SearchEngine for Searx {
|
|
27 |
/// * `query` - Takes the user provided query to query to the upstream search engine with.
|
28 |
/// * `page` - Takes an u32 as an argument.
|
29 |
/// * `user_agent` - Takes a random user agent string as an argument.
|
|
|
30 |
///
|
31 |
/// # Errors
|
32 |
///
|
@@ -40,6 +41,7 @@ impl SearchEngine for Searx {
|
|
40 |
query: String,
|
41 |
page: u32,
|
42 |
user_agent: String,
|
|
|
43 |
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
|
44 |
// Page number can be missing or empty string and so appropriate handling is required
|
45 |
// so that upstream server recieves valid page number.
|
@@ -73,8 +75,9 @@ impl SearchEngine for Searx {
|
|
73 |
);
|
74 |
header_map.insert(COOKIE, "categories=general; language=auto; locale=en; autocomplete=duckduckgo; image_proxy=1; method=POST; safesearch=2; theme=simple; results_on_new_tab=1; doi_resolver=oadoi.org; simple_style=auto; center_alignment=1; query_in_title=1; infinite_scroll=0; disabled_engines=; enabled_engines=\"archive is__general\\054yep__general\\054curlie__general\\054currency__general\\054ddg definitions__general\\054wikidata__general\\054duckduckgo__general\\054tineye__general\\054lingva__general\\054startpage__general\\054yahoo__general\\054wiby__general\\054marginalia__general\\054alexandria__general\\054wikibooks__general\\054wikiquote__general\\054wikisource__general\\054wikiversity__general\\054wikivoyage__general\\054dictzone__general\\054seznam__general\\054mojeek__general\\054naver__general\\054wikimini__general\\054brave__general\\054petalsearch__general\\054goo__general\"; disabled_plugins=; enabled_plugins=\"searx.plugins.hostname_replace\\054searx.plugins.oa_doi_rewrite\\054searx.plugins.vim_hotkeys\"; tokens=; maintab=on; enginetab=on".parse().into_report().change_context(EngineError::UnexpectedError)?);
|
75 |
|
76 |
-
let document: Html =
|
77 |
-
|
|
|
78 |
|
79 |
let no_result: Selector = Selector::parse("#urls>.dialog-error>p")
|
80 |
.map_err(|_| Report::new(EngineError::UnexpectedError))
|
|
|
27 |
/// * `query` - Takes the user provided query to query to the upstream search engine with.
|
28 |
/// * `page` - Takes an u32 as an argument.
|
29 |
/// * `user_agent` - Takes a random user agent string as an argument.
|
30 |
+
/// * `request_timeout` - Takes a time (secs) as a value which controls the server request timeout.
|
31 |
///
|
32 |
/// # Errors
|
33 |
///
|
|
|
41 |
query: String,
|
42 |
page: u32,
|
43 |
user_agent: String,
|
44 |
+
request_timeout: u8,
|
45 |
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
|
46 |
// Page number can be missing or empty string and so appropriate handling is required
|
47 |
// so that upstream server recieves valid page number.
|
|
|
75 |
);
|
76 |
header_map.insert(COOKIE, "categories=general; language=auto; locale=en; autocomplete=duckduckgo; image_proxy=1; method=POST; safesearch=2; theme=simple; results_on_new_tab=1; doi_resolver=oadoi.org; simple_style=auto; center_alignment=1; query_in_title=1; infinite_scroll=0; disabled_engines=; enabled_engines=\"archive is__general\\054yep__general\\054curlie__general\\054currency__general\\054ddg definitions__general\\054wikidata__general\\054duckduckgo__general\\054tineye__general\\054lingva__general\\054startpage__general\\054yahoo__general\\054wiby__general\\054marginalia__general\\054alexandria__general\\054wikibooks__general\\054wikiquote__general\\054wikisource__general\\054wikiversity__general\\054wikivoyage__general\\054dictzone__general\\054seznam__general\\054mojeek__general\\054naver__general\\054wikimini__general\\054brave__general\\054petalsearch__general\\054goo__general\"; disabled_plugins=; enabled_plugins=\"searx.plugins.hostname_replace\\054searx.plugins.oa_doi_rewrite\\054searx.plugins.vim_hotkeys\"; tokens=; maintab=on; enginetab=on".parse().into_report().change_context(EngineError::UnexpectedError)?);
|
77 |
|
78 |
+
let document: Html = Html::parse_document(
|
79 |
+
&Searx::fetch_html_from_upstream(self, url, header_map, request_timeout).await?,
|
80 |
+
);
|
81 |
|
82 |
let no_result: Selector = Selector::parse("#urls>.dialog-error>p")
|
83 |
.map_err(|_| Report::new(EngineError::UnexpectedError))
|
src/results/aggregator.rs
CHANGED
@@ -51,6 +51,7 @@ type FutureVec = Vec<JoinHandle<Result<HashMap<String, RawSearchResult>, Report<
|
|
51 |
/// * `random_delay` - Accepts a boolean value to add a random delay before making the request.
|
52 |
/// * `debug` - Accepts a boolean value to enable or disable debug mode option.
|
53 |
/// * `upstream_search_engines` - Accepts a vector of search engine names which was selected by the
|
|
|
54 |
/// user through the UI or the config file.
|
55 |
///
|
56 |
/// # Error
|
@@ -64,6 +65,7 @@ pub async fn aggregate(
|
|
64 |
random_delay: bool,
|
65 |
debug: bool,
|
66 |
upstream_search_engines: Vec<String>,
|
|
|
67 |
) -> Result<SearchResults, Box<dyn std::error::Error>> {
|
68 |
let user_agent: String = random_user_agent();
|
69 |
let mut result_map: HashMap<String, RawSearchResult> = HashMap::new();
|
@@ -92,9 +94,11 @@ pub async fn aggregate(
|
|
92 |
.map(|search_engine| {
|
93 |
let query: String = query.clone();
|
94 |
let user_agent: String = user_agent.clone();
|
95 |
-
tokio::spawn(
|
96 |
-
|
97 |
-
|
|
|
|
|
98 |
})
|
99 |
.collect();
|
100 |
|
|
|
51 |
/// * `random_delay` - Accepts a boolean value to add a random delay before making the request.
|
52 |
/// * `debug` - Accepts a boolean value to enable or disable debug mode option.
|
53 |
/// * `upstream_search_engines` - Accepts a vector of search engine names which was selected by the
|
54 |
+
/// * `request_timeout` - Accepts a time (secs) as a value which controls the server request timeout.
|
55 |
/// user through the UI or the config file.
|
56 |
///
|
57 |
/// # Error
|
|
|
65 |
random_delay: bool,
|
66 |
debug: bool,
|
67 |
upstream_search_engines: Vec<String>,
|
68 |
+
request_timeout: u8,
|
69 |
) -> Result<SearchResults, Box<dyn std::error::Error>> {
|
70 |
let user_agent: String = random_user_agent();
|
71 |
let mut result_map: HashMap<String, RawSearchResult> = HashMap::new();
|
|
|
94 |
.map(|search_engine| {
|
95 |
let query: String = query.clone();
|
96 |
let user_agent: String = user_agent.clone();
|
97 |
+
tokio::spawn(async move {
|
98 |
+
search_engine
|
99 |
+
.results(query, page, user_agent.clone(), request_timeout)
|
100 |
+
.await
|
101 |
+
})
|
102 |
})
|
103 |
.collect();
|
104 |
|
src/server/routes.rs
CHANGED
@@ -146,6 +146,7 @@ async fn results(
|
|
146 |
config.aggregator.random_delay,
|
147 |
config.debug,
|
148 |
cookie_value.engines,
|
|
|
149 |
)
|
150 |
.await?
|
151 |
}
|
@@ -156,6 +157,7 @@ async fn results(
|
|
156 |
config.aggregator.random_delay,
|
157 |
config.debug,
|
158 |
config.upstream_search_engines.clone(),
|
|
|
159 |
)
|
160 |
.await?
|
161 |
}
|
|
|
146 |
config.aggregator.random_delay,
|
147 |
config.debug,
|
148 |
cookie_value.engines,
|
149 |
+
config.request_timeout,
|
150 |
)
|
151 |
.await?
|
152 |
}
|
|
|
157 |
config.aggregator.random_delay,
|
158 |
config.debug,
|
159 |
config.upstream_search_engines.clone(),
|
160 |
+
config.request_timeout,
|
161 |
)
|
162 |
.await?
|
163 |
}
|
websurfx/config.lua
CHANGED
@@ -8,6 +8,7 @@ binding_ip = "127.0.0.1" --ip address on the which server should be launched.
|
|
8 |
production_use = false -- whether to use production mode or not (in other words this option should be used if it is to be used to host it on the server to provide a service to a large number of users (more than one))
|
9 |
-- if production_use is set to true
|
10 |
-- There will be a random delay before sending the request to the search engines, this is to prevent DDoSing the upstream search engines from a large number of simultaneous requests.
|
|
|
11 |
|
12 |
-- ### Website ###
|
13 |
-- The different colorschemes provided are:
|
|
|
8 |
production_use = false -- whether to use production mode or not (in other words this option should be used if it is to be used to host it on the server to provide a service to a large number of users (more than one))
|
9 |
-- if production_use is set to true
|
10 |
-- There will be a random delay before sending the request to the search engines, this is to prevent DDoSing the upstream search engines from a large number of simultaneous requests.
|
11 |
+
request_timeout = 30 -- timeout for the search requests sent to the upstream search engines to be fetched (value in seconds).
|
12 |
|
13 |
-- ### Website ###
|
14 |
-- The different colorschemes provided are:
|