Release: v0.8.0: search, askTheRabbi, idExtracter

Added search(), askTheRabbi() and idExtracter()

.gitignore

@@ -4,4 +4,5 @@ yarn.lock
 .yarn/
 .pnp.loader.mjs
 .npmrc
-build/
+build/
+package-lock.json

.npmignore

@@ -1,5 +1,5 @@
 .gitignore
-tests/
+test/
 src/
 .yarn/
 .github/

README.md

@@ -8,9 +8,9 @@
 
 > _An (unofficial) API for Hidabroot_
 
-## Important
+## Important notice
 
-This API may be blocked at any time by Hidabroot's team. If any damage caused by this API, it is not my fault, use this API at your own risk.
+This API is unofficial, meaning **I am not responisble for any damage caused by using this API**. This API may be _blocked at any time by Hidabroot's team_. **This API is never stable** as Hidabroot can change at any time their website structure that will break this API.
 
 ## Install
 
@@ -78,6 +78,99 @@ getArticle(1185334).then((result) => console.log(result));
 //gets the content of the article: https://www.hidabroot.org/article/1185334 and then log the content to the console
 ```
 
+### search(query, options?)
+
+#### query
+
+Type: `string`
+
+The query to search for in the website.
+
+#### options
+
+Type: [`searchOptions`](/src/types/search.ts)
+
+The options for the search. Recommended to get better results.
+
+#### Example
+
+```ts
+import { search } from "hidabroot";
+
+const response = await search("האם היו עולמות קודמים?", {
+  searchOptions: { searchType: "faq" }, // "faq" means "Ask The Rabbi" questions
+});
+console.log(response);
+```
+
+Which return to the console something like this:
+
+```json
+{
+  "url for result": "result title"
+}
+```
+
+Currently (`v0.8.0`), the search is capable to return ~10-15 results. This may be changed in the future.
+
+### askTheRabbi(questionID)
+
+#### questionID
+
+Type: `number`
+
+The "Ask The Rabbi" question ID. Can be found in `https://www.hidabroot.org/question/X` where X is the question ID.
+
+#### Example
+
+```ts
+import { askTheRabbi, idExtracter } from "hidabroot";
+
+const questionID = idExtracter("https://www.hidabroot.org/question/75137", {
+  pageType: "askTheRabbi",
+});
+const response = await askTheRabbi(questionID);
+console.log(response);
+```
+
+Which return to the console something like this:
+
+```json
+{
+  "title": "the question title",
+  "question": "the question",
+  "answer": "the rabbi answer"
+}
+```
+
+(or `null` if the page wasn't found or if an error occurred)
+
+### idExtracter(input, options)
+
+#### input
+
+Type: `string`
+
+The input URL of the Hidabroot page to extract the ID from.
+
+#### options
+
+Type: [`idExtracterOptions`](/src/types/idExtracter.ts)
+
+The options for the extract process.
+
+#### Example
+
+```ts
+import { idExtracter } from "hidabroot";
+
+const questionID = idExtracter("https://www.hidabroot.org/question/75137", {
+  pageType: "askTheRabbi",
+});
+console.log(questionID);
+//=> 75137
+```
+
 ## Contributing
 
 All contributions are welcome! Feel free to open an issue (just search the [issue tracker](https://github.com/itsrn/hidabroot/issues) before opening an issue to make sure your issue hasn't already been reported or answered) or a pull request.

package.json

@@ -1,6 +1,6 @@
 {
   "name": "hidabroot",
-  "version": "0.6.4-beta",
+  "version": "0.8.0-beta",
   "description": "An unofficial API for hidabroot",
   "main": "./build/index.js",
   "types": "./build/index.d.ts",
@@ -21,6 +21,7 @@
     "url": "git+https://github.com/itsrn/hidabroot"
   },
   "devDependencies": {
+    "@types/chai": "^4.3.5",
     "@types/mocha": "^10.0.1",
     "@types/node": "^16.10.2",
     "chai": "^4.3.8",

src/askTheRabbi/index.ts

@@ -0,0 +1,61 @@
+import { askTheRabbiResponse } from "../types/askTheRabbi";
+import cheerio from "cheerio";
+
+/**
+ *  Gets the question and answer of "ask the rabbi" question.
+ *
+ * @param {number} questionID The ID of the question. Can be found in `https://www.hidabroot.org/question/X` (X is the question ID).
+ */
+export async function askTheRabbi(
+  questionID: number
+): Promise<askTheRabbiResponse | null> {
+  // the url for the question
+  const url = "https://www.hidabroot.org/question/" + questionID;
+
+  try {
+    // fetches the url of the question
+    return (
+      fetch(url)
+        .then((response) => response.text())
+        // takees the html response
+        .then((html) => {
+          // loads it into cheerio
+          const $ = cheerio.load(html);
+          // gets the header of the question
+          const header = $(".page\\_title.no\\_border").eq(0).text();
+          // if the header indicates that the page was not found
+          if (header == "דף שגיאה 404 - אבל יש לנו הצעות אחרות!...") {
+            // return null
+            return null;
+          } else {
+            // gets the whole div with id "article_inner" and save only the question div in the question variable
+            const question = $("[id=article_inner]").contents().eq(1);
+            // format the question div text content
+            const formattedQuestion =
+              question.text().replace(/\s+/g, " ").replace(/<br>/g, "\n") || "";
+            // gets the whole div with id "article_inner" and save only the answer div in the answer variable
+            const answer = $("[id=article_inner]").contents().eq(1);
+            // format the answer div text content
+            const formattedAnswer =
+              answer.text().replace(/\s+/g, " ").replace(/<br>/g, "\n") || "";
+            // saves the json response
+            const jsonResponse = {
+              title: header,
+              question: formattedQuestion,
+              answer: formattedAnswer,
+            };
+
+            // returns the json response
+            return jsonResponse;
+          }
+        })
+        .catch((error) => {
+          console.error("Error: " + error);
+          return null;
+        })
+    );
+  } catch (e) {
+    console.error("Error: " + e);
+    return null;
+  }
+}

src/getArticle/index.ts

@@ -6,29 +6,42 @@ import cheerio from "cheerio";
  * @param {number} id The id of the article
  */
 export async function getArticle(id: number): Promise<string | null> {
+  // the url for the article
   const url = "https://www.hidabroot.org/article/" + id;
 
   try {
-    return fetch(url)
-      .then((response) => response.text())
-      .then((html) => {
-        const $ = cheerio.load(html);
-        const header = $(".page\\_title.no\\_border").eq(0).text();
-        let output: string | null = "";
-        if (header == "דף שגיאה 404 - אבל יש לנו הצעות אחרות!...") {
-          output = null;
-        } else {
-          $('p[dir="RTL"]').each((index, p) => {
-            output += $(p).text();
-          });
-        }
+    // fetches the article
+    return (
+      fetch(url)
+        .then((response) => response.text())
+        // takes the html response
+        .then((html) => {
+          // loads it into cheerio
+          const $ = cheerio.load(html);
+          // gets the header of the article
+          const header = $(".page\\_title.no\\_border").eq(0).text();
+          // create an output variable to contain the article content or null if it doesn't exist
+          let output: string | null = "";
+          // if the header says that the page is 404
+          if (header == "דף שגיאה 404 - אבל יש לנו הצעות אחרות!...") {
+            // set the output to null
+            output = null;
+          } else {
+            // if it does exist, search for every <p> tag with attribute dir="RTL"
+            $('p[dir="RTL"]').each((index, p) => {
+              // for every <p> tag, add the text of the found <p> tag to the variable output
+              output += $(p).text();
+            });
+          }
 
-        return output;
-      })
-      .catch((error) => {
-        console.error("Error: " + error);
-        return null;
-      });
+          // return the output variable
+          return output;
+        })
+        .catch((error) => {
+          console.error("Error: " + error);
+          return null;
+        })
+    );
   } catch (err) {
     console.error("Error:", err);
     return null;

src/idExtracter/index.ts

@@ -0,0 +1,81 @@
+import { idExtracterOptions } from "../types/idExtracter";
+
+/**
+ * Extract IDs from any article, "Ask The Rabbi" question page or anything else that exists on Hidabroot's website. Returns null if the page isn't a valid Hidabroot page URL.
+ *
+ * @param {string} input A URL for the page you want to extract the ID from.
+ * @param {idExtracterOptions} options Options for extracting the ID.
+ */
+export function idExtracter(
+  input: string,
+  options: idExtracterOptions
+): number | null {
+  if (
+    input.startsWith("www.hidabroot.org/") ||
+    input.startsWith("http://www.hidabroot.org/") ||
+    input.startsWith("https://www.hidabroot.org/") ||
+    input.startsWith("hidabroot.org/")
+  ) {
+    if (options.pageType == "askTheRabbi") {
+      if (input.startsWith("http://www.hidabroot.org/")) {
+        const id = input
+          .replace("http://www.hidabroot.org/question/", "")
+          .trim();
+        return Number(id);
+      } else if (input.startsWith("https://www.hidabroot.org/")) {
+        const id = input
+          .replace("https://www.hidabroot.org/question/", "")
+          .trim();
+        return Number(id);
+      } else if (input.startsWith("www.hidabroot.org/")) {
+        const id = input.replace("hidabroot.org/question/", "").trim();
+        return Number(id);
+      } else if (input.startsWith("hidabroot.org/")) {
+        const id = input.replace("hidabroot.org/question/", "").trim();
+        return Number(id);
+      } else {
+        return null;
+      }
+    } else if (options.pageType == "article") {
+      if (input.startsWith("http://www.hidabroot.org/")) {
+        const id = input
+          .replace("http://www.hidabroot.org/article/", "")
+          .trim();
+        return Number(id);
+      } else if (input.startsWith("https://www.hidabroot.org/")) {
+        const id = input
+          .replace("https://www.hidabroot.org/article/", "")
+          .trim();
+        return Number(id);
+      } else if (input.startsWith("www.hidabroot.org/")) {
+        const id = input.replace("hidabroot.org/article/", "").trim();
+        return Number(id);
+      } else if (input.startsWith("hidabroot.org/")) {
+        const id = input.replace("hidabroot.org/article/", "").trim();
+        return Number(id);
+      } else {
+        return null;
+      }
+    } else if (options.pageType == "video") {
+      if (input.startsWith("http://www.hidabroot.org/")) {
+        const id = input.replace("http://www.hidabroot.org/video/", "").trim();
+        return Number(id);
+      } else if (input.startsWith("https://www.hidabroot.org/")) {
+        const id = input.replace("https://www.hidabroot.org/video/", "").trim();
+        return Number(id);
+      } else if (input.startsWith("www.hidabroot.org/")) {
+        const id = input.replace("hidabroot.org/video/", "").trim();
+        return Number(id);
+      } else if (input.startsWith("hidabroot.org/")) {
+        const id = input.replace("hidabroot.org/video/", "").trim();
+        return Number(id);
+      } else {
+        return null;
+      }
+    } else {
+      return null;
+    }
+  } else {
+    return null;
+  }
+}

src/index.ts

@@ -1,4 +1,7 @@
 import { todayNews } from "./todayNews";
 import { getArticle } from "./getArticle";
+import { askTheRabbi } from "./askTheRabbi";
+import { search } from "./search";
+import { idExtracter } from "./idExtracter";
 
-export { todayNews, getArticle };
+export { todayNews, getArticle, askTheRabbi, search, idExtracter };