dms-scrape 0.4.4 → 0.4.6

package/sources/T4/TAISOUNDS.mjs

@@ -1,21 +0,0 @@
-export function TAISOUNDS($) {
-  const data = $.extract({
-    date: [
-      {
-        selector: "div.publish",
-        value: (el, key) => {
-          const eachValue = $(el).text().trim();
-          if (eachValue !== "") {
-            return eachValue.slice(0, 10);
-          }
-        },
-      },
-    ],
-    
-  });
-  data["title"] = $("div.news-box h1").text();
-  data["source"] = "太報";
-  data["author"] = $("a[href^='/more/reporternews']").text();
-  data["content"] = $("div.news-box-text.border").html().split("\n").filter((item) => item.includes("<br>")).toString().split(/<\/?[^>]+>/).filter((item)=> item != '')
-  return data;
-}

package/sources/T5/CNYES.mjs

@@ -1,25 +0,0 @@
-export function CNYES($) {
-  const data = $.extract({
-    title: [{ selector: "title", value: (el) => $(el).text().trim() }],
-    date: [
-      {
-        selector: "p:contains('2024'):first",
-        value: (el) => $(el).text().split("  ")[1].split(" ")[0],
-      },
-    ],
-    author: [
-      {
-        selector: "p:contains('2024'):first",
-        value: (el) => $(el).text().split("  ")[0].replace(" ", ""),
-      },
-    ],
-    content: [
-      {
-        selector: "main#article-container section p",
-        value: (el) => $(el).text().trim(),
-      },
-    ],
-  });
-  data["source"] = "鉅亨網"
-  return data;
-}

package/sources/T5/COMPOTECHASIA.mjs

@@ -1,30 +0,0 @@
-export function COMPOTECHASIA($) {
-  const data = $.extract({
-    title: [
-      {
-        selector: "title",
-        value: (el) => $(el).text().trim().replace("_COMPOTECH ASIA", ""),
-      },
-    ],
-    date: [
-        {
-            selector: "span.deta",
-            value: (el) => $(el).text().split(" ")[0]
-        }
-    ],
-    author: [
-        {
-            selector: "span:contains('本文作者：') > a",
-            value: (el) => $(el).text().trim()
-        }
-    ],
-    content: [
-        {
-            selector: "div.article_wz_text div",
-            value: (el) => $(el).text()
-        }
-    ]
-  });
-  data["source"] = "智慧電子解決方案設計平台"
-  return data
-}

package/sources/T5/COOL3C.mjs

@@ -1,26 +0,0 @@
-export function COOL3C($) {
-  let data = {};
-  data["title"] = $("li.breadcrumb-item.active")
-    .text()
-    .trim()
-    .replace("\n", "");
-  data["date"] = $("div.created.slacken span")
-    .eq(1)
-    .text()
-    .trim()
-    .split(" ")[0]
-    .replace(/\./g, "-");
-  data["author"] = $("div.author a").text().trim();
-
-  data["content"] = [];
-  $("div.row.content div p").each(function () {
-    const text = $(this).html().trim();
-    if (text.startsWith("<img") || text.startsWith("▲")) {
-      return;
-    } else {
-      data["content"].push(text.replace("undefined", "").trim());
-    }
-  });
-  data["source"] = "Cool3c";
-  return data;
-}

package/sources/T5/EPRICE.mjs

@@ -1,19 +0,0 @@
-export function EPRICE($) {
-  const data = $.extract({
-    headline: "h1.title",
-  });
-  data["date"] = $("span.date")
-    .first()
-    .text()
-    .replace(/.*?(\d{4}-\d{2}-\d{2}).*/, "$1");
-  data["author"] = $("a.nickname").first().attr("title");
-
-  data["content"] = $("div.user-comment-block")
-    .first()
-    .html() // Get inner HTML of the div
-    .split(/<br\s*\/?>\s*<br\s*\/?>/i) // Split by two consecutive <br> tags
-    .map((line) => line.trim()) // Trim whitespace from each line
-    .filter((line) => line.length > 0);
-    data["source"] = "ePrice"
-  return data;
-}

package/sources/T5/INSIDE.mjs

@@ -1,15 +0,0 @@
-export function INSIDE($) {
-  const data = $.extract({
-    title: [{ selector: "title", value: (el) => $(el).text().trim() }],
-    author: "a.author.url.fn",
-    date: [
-      {
-        selector: "li.post_date:first span",
-        value: (el) => $(el).text().replace(/\//g, "-"),
-      },
-    ],
-    content: [{ selector: "section.js-article-content-body p" }],
-  });
-  data["source"] = "Inside"
-  return data;
-}

package/sources/T5/KOCPC.mjs

@@ -1,28 +0,0 @@
-export function KOCPC($) {
-  let data = {};
-
-  data["title"] = $("h1.jeg_post_title").text();
-  data["date"] = $('div.jeg_meta_date > a')
-    .text()
-    .replace(/(\d{4}) 年 (\d{2}) 月 (\d{2}) 日/, "$1-$2-$3");
-  data["source"] = "電腦王阿達";
-  data["author"] = $("div.jeg_meta_author a").text();
-  data["content"] = [];
-// data['category'] = $("meta")
-  //Zi_ad_ar_iR
-
-  $("div.Zi_ad_ar_iR p").each((index, element) => {
-    if (
-      !$(element).text().trim() == "" &&
-      !$(element).text().startsWith("<img")
-    ) {
-      data["content"].push(
-        $(element)
-          .text()
-          .trim()
-          .replace(/<[^>]*>/g, "")
-      );
-    }
-  });
-  return data;
-}

package/sources/T5/MASHDIGI.mjs

@@ -1,27 +0,0 @@
-export function MASHDIGI($) {
-  let data = {};
-  const link = $('link[rel="canonical"]').attr('href')
-  data["title"] = $("h1.entry-title").text().trim();
-  data["date"] = $('[href="' + link + '"] > time.entry-date.published').text();
-  data["author"] = $("div.entry-meta span.author.vcard")
-    .text()
-    .replace(" (Mash Yang)", "");
-
-  data["content"] = [];
-  $("div.bialty-container p").each(function () {
-    const htmlContent = $(this).html().trim();
-    const textContent = $(this).text().trim();
-
-    if (
-      htmlContent.includes("<img") ||
-      textContent.startsWith("▲") ||
-      textContent === ""
-    ) {
-      return;
-    } else {
-      data["content"].push(textContent.replace("undefined", "").trim());
-    }
-  });
-  data["source"] = "Mashdigi";
-  return data;
-}

package/sources/T5/SAYDIGI.mjs

@@ -1,22 +0,0 @@
-export function SAYDIGI($) {
-  const data = $.extract({
-    title: [{ selector: "title", value: (el) => $(el).text().trim() }],
-    date: [
-      {
-        selector: "meta[property=article:modified_time]",
-        value: (el) => $(el).attr("content").split("T")[0],
-      },
-    ],
-    author: [
-      { selector: "meta[name=author]", value: (el) => $(el).attr("content") },
-    ],
-    content: [
-      {
-        selector: "div.cttt > p",
-        value: (el) => $(el).text().trim(),
-      },
-    ],
-  });
-  data["source"] = "點子生活"
-  return data;
-}

package/sources/T5/SOGI.mjs

@@ -1,46 +0,0 @@
-export function SOGI($) {
-  const data = $.extract({
-    title: "h1.h1",
-    author: [
-      {
-        selector: "div.d-inline-block.mr-3",
-        value: function (el, key) {
-          let cleanedText = $(el)
-            .text()
-            .trim()
-            .replace(/[\n\s]/g, "");
-          if (cleanedText.includes("特約編輯")) {
-            var match = cleanedText.match(/by(.*?)特約編輯/);
-          } else if (cleanedText.includes("編輯")) {
-            var match = cleanedText.match(/by(.*?)編輯/);
-          } else {
-            var match = null;
-          }
-          if (match) {
-            let result = match[1]; // This will give you the text between "by" and "特約編輯"
-            return result.trim(); // Trimming in case there are extra spaces
-          } else {
-            console.log("No match found");
-          }
-        },
-      },
-    ],
-  });
-
-  data["date"] = $("div.d-inline-block.mr-3")
-    .first()
-    .text()
-    .replace("\n", "")
-    .trim()
-    .replace(/\//g, "-");
-
-  data["content"] = $("div.editable.my-2")
-    .html() // Get inner HTML of the div
-    .split(/<br\s*\/?>\s*<br\s*\/?>/i) // Split by two consecutive <br> tags
-    .map((line) => line.trim()) // Trim whitespace from each line
-    .filter((line) => line.length > 0);
-
-    data["source"] = "手機王"
-
-  return data;
-}

package/sources/T5/TECHBANG.mjs

@@ -1,20 +0,0 @@
-export function TECHBANG($) {
-  const data = $.extract({
-    title: [{ selector: "title", value: (el) => $(el).text().trim() }],
-    date: [
-      {
-        selector: "meta[property=article:published_time]",
-        value: (el) => $(el).attr("content").split("T")[0],
-      },
-    ],
-    author: "a.nickname:first",
-    content: [
-        {
-          selector: "div.article-content > p",
-          value: (el) => $(el).text().trim(),
-        },
-      ],
-  });
-  data["source"] = "T客邦"
-  return data;
-}

package/sources/T5/TECHNEWS.mjs

@@ -1,17 +0,0 @@
-export function TECHNEWS($) {
-  let data = {};
-  data["title"] = $("h1.entry-title").text();
-  data["content"] = [];
-  let dateParts = $("span.body:nth-of-type(4)")
-    .text()
-    .match(/(\d{4}) 年 (\d{2}) 月 (\d{2}) 日/);
-  data["date"] = `${dateParts[1]}-${dateParts[2]}-${dateParts[3]}`;
-  data["source"] = "科技新報";
-  data["author"] = $("[rel=author]").text().replace(" ", "");
-
-  $("div.indent p").each((i, element) => {
-    data["content"].push($(element).text().trim());
-  });
-
-  return data;
-}

package/sources/T5/TECHORANGE.mjs

@@ -1,26 +0,0 @@
-export function TECHORANGE($) {
-  const data = $.extract({
-    title: [{ selector: "title", value: (el) => $(el).text().trim() }],
-
-    date: [
-      {
-        selector: "meta[property=article:modified_time]",
-        value: (el) => $(el).attr("content").split("T")[0],
-      },
-    ],
-    author: [
-      {
-        selector: "meta[name=twitter:data1]",
-        value: (el) => $(el).attr('content'),
-      },
-    ],
-    content: [
-      {
-        selector: "div.elementor-widget-container > p",
-        value: (el) => $(el).text().trim(),
-      },
-    ],
-  });
-  data["source"] = "科技報橘"
-  return data;
-}

package/sources/T5/XF.mjs

@@ -1,28 +0,0 @@
-export function XF($) {
-  let data = {};
-  data["title"] = $("span#thread_subject").text();
-
-  const input = $('em[id^="authorposton"]').text();
-
-  // Regular expression to match the date part and capture the year, month, and day
-  const regex = /發表於 (\d{4})-(\d{1,2})-(\d{1,2})/;
-
-  // Replace the matched date with the desired format
-  const formattedDate = input.replace(regex, (match, year, month, day) => {
-    // Ensure month and day are zero-padded to two digits
-    const paddedMonth = month.padStart(2, "0");
-    const paddedDay = day.padStart(2, "0");
-    return `${year}-${paddedMonth}-${paddedDay}`;
-  });
-  data["date"] = formattedDate.slice(0, 10);
-  data["source"] = "XFastest";
-  data["author"] = $("a[href^='space-uid']").last().text();
-  $('td[id^="post"]').each((index, element) => {
-    let content = $(element)
-      .html()
-      .split(/<\/?[^>]+>/)
-      .map((item) => item.trim()); // Trim all elements
-    data["content"] = content;
-  });
-  return data;
-}