.envrc

@@ -1 +0,0 @@
-use flake

.gitignore

@@ -5,4 +5,3 @@ node_modules
 /target
 nzz/
 result
-.direnv/

Cargo.toml

@@ -5,10 +5,10 @@ members = [
 ]
 
 [workspace.dependencies]
-anyhow = "1.0.96"
-clap = { version = "4.5.30", features = ["env", "derive"] }
+anyhow = "1.0.86"
+clap = { version = "4.5.8", features = ["env", "derive"] }
 serde_json = "1.0.120"
-tokio = { version = "1.43.0", features = ["full"] }
+tokio = { version = "1", features = ["full"] }
 
 [workspace.package]
 license = "AGPL-3.0"

README.md

@@ -76,9 +76,9 @@ nzz-cookie -u 'myuser@example.com' <pw | nzz-download -f 2024-06-01 -t 2024-06-0
 
 ## Caveats
 
-There are no retries on a failed downloads so far, it just crashes. Stemming
-from that I would advise not to try and download big ranges at once until that
-is fixed.
+There are no retries on a failed download so far, it just crashes. Stemming from
+that I would advise not to try and download big ranges at once until that is
+fixed.
 
 ## License
 

cookie/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "nzz-cookie"
-version = "0.3.0"
+version = "0.1.0"
 edition = "2021"
 license =  { workspace = true }
 authors =  { workspace = true }
@@ -9,7 +9,7 @@ repository =  { workspace = true }
 [dependencies]
 anyhow = { workspace = true }
 clap = { workspace = true }
-fantoccini = "0.21.4"
+fantoccini = "0.19.3"
 serde_json = { workspace = true }
 tokio = { workspace = true }
 

cookie/src/lib.rs

@@ -30,20 +30,6 @@ pub async fn run(args: Config, pw: &str) -> Result<()> {
         .await?;
 
     client.goto(LOGIN_URL).await?;
-
-    sleep(Duration::from_millis(500)).await;
-
-    // Sometimes cookie notice has to bee accepted, not sure when though
-    if client.find(Locator::Css(".cmpboxbtncustom")).await.is_ok() {
-        let fu_open_button: Element = element_from_css(&client, ".cmpboxbtncustom").await?;
-        fu_open_button.click().await?;
-
-        let fu_button: Element = element_from_css(&client, ".cmpboxbtn.cmpboxbtnyes.cmpboxbtnyescustomchoices.cmptxt_btn_save").await?;
-        sleep(Duration::from_millis(500)).await;
-        fu_button.click().await?;
-    }
-
-
     let login_button: Element = element_from_css(&client, ".fup-menu-login-container").await?;
     sleep(Duration::from_millis(500)).await;
     login_button.click().await?;

download/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "nzz-download"
-version = "0.3.0"
+version = "0.1.0"
 edition = "2021"
 license =  { workspace = true }
 authors =  { workspace = true }
@@ -9,12 +9,12 @@ repository =  { workspace = true }
 [dependencies]
 anyhow = { workspace = true }
 clap = { workspace = true }
-lopdf = "0.35.0"
-reqwest = { version = "0.12.12", features = ["json"] }
-serde = { version = "1.0.218", features = ["derive"] }
+lopdf = "0.32.0"
+reqwest = { version = "0.12.5", features = ["json"] }
+serde = { version = "1.0.203", features = ["derive"] }
 serde_json = { workspace = true }
-tempfile = "3.17.1"
+tempfile = "3.10.1"
 tokio = { workspace = true }
-time = { version = "0.3.37", features = ["macros", "serde", "formatting", "parsing" ] }
-tracing = "0.1.41"
-tracing-subscriber = "0.3.19"
+time = { version = "0.3.36", features = ["macros", "serde", "formatting", "parsing" ] }
+tracing = "0.1.40"
+tracing-subscriber = "0.3.18"

download/src/download.rs

@@ -17,10 +17,7 @@ const MAX_DOWNLOADS: usize = 4;
 
 /// Fetch a single newspaper issue and save the merged pdf to `output_dir`.
 async fn fetch_issue(issue: &Issue, output_dir: PathBuf) -> Result<()> {
-    info!(
-        "saving issue {} ({})",
-        issue.publication_date, issue.edition
-    );
+    info!("saving issue {}", issue.publication_date);
 
     let client = reqwest::Client::new();
     let tmp_dir = tempfile::tempdir()?;
@@ -42,13 +39,9 @@ async fn fetch_issue(issue: &Issue, output_dir: PathBuf) -> Result<()> {
         pages.push(tmp_page);
     }
 
-    let issue_name = format!(
-        "nzz_{}_{}.pdf",
-        issue.publication_date,
-        issue.edition.to_lowercase()
-    );
+    let issue_name = format!("nzz_{}.pdf", issue.publication_date);
     let issue_path = output_dir.join(issue_name);
-    let issue_title = format!("NZZ {} ({})", issue.publication_date, issue.edition);
+    let issue_title = format!("NZZ {}", issue.publication_date);
 
     pdf::merge(pages, &issue_path, &issue_title)?;
     debug!("issue {} saved", issue.publication_date);

download/src/nzz.rs

@@ -12,16 +12,14 @@ const SEARCH_URL: &str = "https://zeitungsarchiv.nzz.ch/solr-epaper-search/1.0/s
 const ISSUE_URL: &str = "https://zeitungsarchiv.nzz.ch/archive/1.0/getPages";
 const MAX_DOWNLOADS: usize = 4;
 
-#[derive(Debug, Serialize, Deserialize)]
-struct SortOption {
-    field: String,
-    order: String,
-}
-
 #[derive(Debug, Serialize, Deserialize)]
 struct SearchData {
     query: String,
     offset: u32,
+    #[serde(rename = "sortField")]
+    sort_field: String,
+    #[serde(rename = "sortOrder")]
+    sort_order: String,
     #[serde(
         rename = "startDate",
         serialize_with = "crate::date::serialize",
@@ -34,8 +32,6 @@ struct SearchData {
         deserialize_with = "crate::date::deserialize"
     )]
     end_date: Date,
-    #[serde(rename = "sortOptions")]
-    sort_options: Vec<SortOption>,
 }
 
 #[derive(Debug, Serialize, Deserialize)]
@@ -64,7 +60,6 @@ struct IssueData {
         deserialize_with = "crate::date::deserialize"
     )]
     publication_date: Date,
-    issue: String,
 }
 
 #[derive(Debug, Serialize, Deserialize)]
@@ -101,8 +96,6 @@ struct PageHighRes {
 pub struct Issue {
     /// Date of publication.
     pub publication_date: Date,
-    /// Edition name (used to have multiple issues on the same date).
-    pub edition: String,
     /// ordered vector of page urls in the issue.
     pub pages: Vec<String>,
 }
@@ -112,10 +105,8 @@ impl SearchData {
         Self {
             query: "".to_string(),
             offset,
-            sort_options: vec![SortOption {
-                field: "media_ts".to_string(),
-                order: "desc".to_string(),
-            }],
+            sort_field: "media_ts".to_string(),
+            sort_order: "desc".to_string(),
             start_date,
             end_date,
         }
@@ -183,16 +174,6 @@ async fn build_pages(cookie: &str, edition_id: u32) -> Result<Vec<String>> {
     Ok(pages)
 }
 
-/// Convert the various issue names to their descriptive equivalent.
-fn convert_issue_name(issue: &str) -> String {
-    match issue {
-        "Zürich" => "01 (Morgenausgabe)".into(),
-        "Ausgabe 02" => "02 (Mittagausgabe)".into(),
-        "Ausgabe 03" => "03 (Abendausgabe)".into(),
-        _ => unreachable!(),
-    }
-}
-
 /// Fetch all page urls for `issues`.
 async fn build_issues(cookie: &str, issues: Vec<IssueData>) -> Result<Vec<Issue>> {
     let mut hydrated_issues = Vec::new();
@@ -213,7 +194,6 @@ async fn build_issues(cookie: &str, issues: Vec<IssueData>) -> Result<Vec<Issue>
             let pages = build_pages(&cookie, issue.edition_id).await?;
             Ok(Issue {
                 publication_date: issue.publication_date,
-                edition: convert_issue_name(&issue.issue),
                 pages,
             })
         });

download/src/pdf.rs

@@ -48,8 +48,8 @@ pub fn merge(input: Vec<PathBuf>, out: &Path, title: &str) -> Result<()> {
     for (object_id, object) in documents_objects.iter() {
         // We have to ignore "Page" (as are processed later), "Outlines" and "Outline" objects
         // All other objects should be collected and inserted into the main Document
-        match object.type_name().unwrap_or(b"") {
-            b"Catalog" => {
+        match object.type_name().unwrap_or("") {
+            "Catalog" => {
                 // Collect a first "Catalog" object and use it for the future "Pages"
                 catalog_object = Some((
                     if let Some((id, _)) = catalog_object {
@@ -60,7 +60,7 @@ pub fn merge(input: Vec<PathBuf>, out: &Path, title: &str) -> Result<()> {
                     object.clone(),
                 ));
             }
-            b"Pages" => {
+            "Pages" => {
                 // Collect and update a first "Pages" object and use it for the future "Catalog"
                 // We have also to merge all dictionaries of the old and the new "Pages" object
                 if let Ok(dictionary) = object.as_dict() {
@@ -81,9 +81,9 @@ pub fn merge(input: Vec<PathBuf>, out: &Path, title: &str) -> Result<()> {
                     ));
                 }
             }
-            b"Page" => {}     // Ignored, processed later and separately
-            b"Outlines" => {} // Ignored, not supported yet
-            b"Outline" => {}  // Ignored, not supported yet
+            "Page" => {}     // Ignored, processed later and separately
+            "Outlines" => {} // Ignored, not supported yet
+            "Outline" => {}  // Ignored, not supported yet
             _ => {
                 merged_doc.max_id += 1;
                 merged_doc.objects.insert(*object_id, object.clone());

flake.nix

@@ -1,4 +1,4 @@
-# thanks to https://code.betamike.com/micropelago/domani for the flake, I still do not completely understand it :)
+# thanks to https://code.betamike.com/micropelago/domani for the flake, I still do not completely understand it :) 
 {
   description = "little-hesinde project";
   inputs = {
@@ -21,7 +21,7 @@
         fenixPkgs:
         fenixPkgs.fromToolchainFile {
           file = ./rust-toolchain.toml;
-          sha256 = "sha256-AJ6LX/Q/Er9kS15bn9iflkUwcgYqRQxiOIL2ToVAXaU=";
+          sha256 = "sha256-Ngiz76YP4HTY75GGdH2P+APE/DEIx2R/Dn+BwwOyzZU=";
         };
 
       buildTargets = {

rust-toolchain.toml

@@ -1,4 +1,4 @@
 [toolchain]
 channel = "stable"
 targets = [ "i686-unknown-linux-musl", "aarch64-unknown-linux-musl", "x86_64-unknown-linux-musl" ]
-profile = "default"
+profile = "minimal"