因應 FB 改版，調整登入元素的 Class、搜尋粉絲頁面的文字分析及 Class

dean9703111 · Aug 18, 2022 · 57adff5 · 57adff5
1 parent 6ae46ad
commit 57adff5
Show file tree

Hide file tree

Showing 21 changed files with 127 additions and 88 deletions.
diff --git a/README.md b/README.md
@@ -79,8 +79,9 @@
 > **2021.11.18**：因應 IG 改版，調整登入檢測程式；並修改部分範例連結，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/fe7118dceb474150a93320d7db82b7edcbdd5b87)  
 > **2021.12.13**：因應 IG 改版，調整抓取追蹤人數的 XPath，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/854245776e6631f27fd8957be8df891791d6d3c0)  
 > **2021.12.17**：因應 IG 改版，調整抓取追蹤人數的 XPath(IG 最近很喜歡改來改去的 QQ)，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/7836528ae38606af2edb05bfc1fec101f705e127)  
-> **2021.2.13**：因應 IG 改版，調整抓取追蹤人數的 XPath(IG 常常會有路徑上細微的調整)，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/1736b56e3a3fb341c6f3d37b8b88b801c545d8da)  
-> **2021.3.22**：因應 FB 改版，調整確認是否登入的 Class，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/0583009d8aa24613e7a409d7ba51daeab11f7968)  
-> **2021.4.27**：因應 FB 改版，調整搜尋粉絲頁面的文字分析，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/199ec02b328a8731e400bc18baded1270ab45965)  
-> **2021.6.1**：因應 IG 改版，粉絲人數原本用 Xpath，現在改用 Class 來抓，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/630a00b6f1b1a2cdb5f9fb46ad30aaf36ea5f1c6)  
-> **2021.7.14**：因應 FB 改版，當追蹤人數破萬後不顯示詳細數據，故將前往搜尋頁面的程式註解，並調整原程式架構，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/5f0ddfb58102958c9b918ad77feb9cc81af50310)  
+> **2022.2.13**：因應 IG 改版，調整抓取追蹤人數的 XPath(IG 常常會有路徑上細微的調整)，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/1736b56e3a3fb341c6f3d37b8b88b801c545d8da)  
+> **2022.3.22**：因應 FB 改版，調整確認是否登入的 Class，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/0583009d8aa24613e7a409d7ba51daeab11f7968)  
+> **2022.4.27**：因應 FB 改版，調整搜尋粉絲頁面的文字分析，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/199ec02b328a8731e400bc18baded1270ab45965)  
+> **2022.6.1**：因應 IG 改版，粉絲人數原本用 Xpath，現在改用 Class 來抓，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/630a00b6f1b1a2cdb5f9fb46ad30aaf36ea5f1c6)  
+> **2022.7.14**：因應 FB 改版，當追蹤人數破萬後不顯示詳細數據，故將前往搜尋頁面的程式註解，並調整原程式架構，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/5f0ddfb58102958c9b918ad77feb9cc81af50310)  
+> **2021.8.19**：因應 FB 改版，調整登入元素的 Class、搜尋粉絲頁面的文字分析及 Class，相關 commit 請看：[連結](https://github.com/dean9703111/social_crawler/commit/199ec02b328a8731e400bc18baded1270ab45965)  
diff --git a/ch12/index.js b/ch12/index.js
@@ -62,7 +62,7 @@ async function loginFacebookGetTrace () {
   login_ele.click();
 
   // 用登入後才有的元件，來判斷是否登入
-  await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"oajrlxb2")]`)));
+  await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"om3e55n1")]`)));
 
   // 前往粉專頁面
   const fan_page = "https://www.facebook.com/baobaonevertell/";
@@ -72,7 +72,7 @@ async function loginFacebookGetTrace () {
   let fb_trace = null; // 這是紀錄FB追蹤人數
   let is_accurate = true; // 確認追蹤人數是否精準
   // 因為考慮到每個粉專顯示追蹤人數的位置都不一樣，所以就採用全抓再分析
-  const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"lrazzd5p")]`)));
+  const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"g4qalytl")]`)));
   for (const fb_trace_ele of fb_trace_eles) {
     const fb_text = await fb_trace_ele.getText();
     if (fb_text.includes('位追蹤者')) { // 新版顯示方式
@@ -85,15 +85,17 @@ async function loginFacebookGetTrace () {
       }
       break;
     } else if (fb_text.includes('個讚')) {
-      fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+      fb_trace = fb_text.
+        substr(0, fb_text.indexOf('個讚')). // 先移除後面字串
+        replace(/\D/g, ''); // 只取數字
     }
   }
   if (fb_trace === null) {
-    const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"b1v8xokw")]`)));
+    const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"pbevjfx6")]`)));
     for (const fb_trace_ele of fb_trace_eles2) {
       const fb_text = await fb_trace_ele.getText();
       if (fb_text.includes('人在追蹤')) { // 經典版顯示方式
-          fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+        fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
         break;
       }
     }

diff --git a/ch14/index.js b/ch14/index.js
@@ -64,7 +64,7 @@ async function loginInstagramGetTrace (driver) {
   let ig_trace = null;//這是紀錄IG追蹤人數
   // const ig_trace_xpath = `//*[@id="react-root"]/section/main/div/header/section/ul/li[2]/a/div/span`;
   // 原本的 Xpath 被 IG 改掉了，改用 Class 來抓
-  const ig_trace_xpath =`//*[contains(@class,"_ac2a")]`
+  const ig_trace_xpath = `//*[contains(@class,"_ac2a")]`;
   const ig_trace_eles = await driver.wait(until.elementsLocated(By.xpath(ig_trace_xpath)));
   // 剛好這個 Class 只有 3 個，我們需要的資訊在第 2 個 Class，IG 因為當人數破萬時會縮寫顯示，所以改抓title
   const ig_text = await ig_trace_eles[1].getAttribute('title');
@@ -89,7 +89,7 @@ async function loginFacebookGetTrace (driver) {
   login_ele.click();
 
   //用登入後才有的元件，來判斷是否登入
-  await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"oajrlxb2")]`)));
+  await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"om3e55n1")]`)));
 
   //前往粉專頁面
   const fan_page = "https://www.facebook.com/baobaonevertell/";
@@ -99,7 +99,7 @@ async function loginFacebookGetTrace (driver) {
   let fb_trace = null;//這是紀錄FB追蹤人數
   let is_accurate = true;//確認追蹤人數是否精準
   //因為考慮到每個粉專顯示追蹤人數的位置都不一樣，所以就採用全抓再分析
-  const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"lrazzd5p")]`)));
+  const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"g4qalytl")]`)));
   for (const fb_trace_ele of fb_trace_eles) {
     const fb_text = await fb_trace_ele.getText();
     if (fb_text.includes('位追蹤者')) { // 新版顯示方式
@@ -112,15 +112,17 @@ async function loginFacebookGetTrace (driver) {
       }
       break;
     } else if (fb_text.includes('個讚')) {
-      fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+      fb_trace = fb_text.
+        substr(0, fb_text.indexOf('個讚')). // 先移除後面字串
+        replace(/\D/g, ''); // 只取數字
     }
   }
   if (fb_trace === null) {
-    const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"b1v8xokw")]`)));
+    const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"pbevjfx6")]`)));
     for (const fb_trace_ele of fb_trace_eles2) {
       const fb_text = await fb_trace_ele.getText();
       if (fb_text.includes('人在追蹤')) { // 經典版顯示方式
-          fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+        fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
         break;
       }
     }

diff --git a/ch15/tools/crawlerFB.js b/ch15/tools/crawlerFB.js
@@ -33,14 +33,14 @@ async function loginFacebook (driver) {
 
   //因為登入這件事情要等Server回應，你直接跳轉粉絲專頁會導致登入失敗
   //用登入後才有的元件，來判斷是否登入
-  await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"oajrlxb2")]`)));
+  await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"om3e55n1")]`)));
 }
 
 async function getTrace (driver, fan_page_name) {
   let fb_trace = null;//這是紀錄FB追蹤人數
   let is_accurate = true;//確認追蹤人數是否精準
   //因為考慮到每個粉專顯示追蹤人數的位置都不一樣，所以就採用全抓再分析
-  const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"lrazzd5p")]`)));
+  const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"g4qalytl")]`)));
   for (const fb_trace_ele of fb_trace_eles) {
     const fb_text = await fb_trace_ele.getText();
     if (fb_text.includes('位追蹤者')) { // 新版顯示方式
@@ -53,15 +53,17 @@ async function getTrace (driver, fan_page_name) {
       }
       break;
     } else if (fb_text.includes('個讚')) {
-      fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+      fb_trace = fb_text.
+        substr(0, fb_text.indexOf('個讚')). // 先移除後面字串
+        replace(/\D/g, ''); // 只取數字
     }
   }
   if (fb_trace === null) {
-    const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"b1v8xokw")]`)));
+    const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"pbevjfx6")]`)));
     for (const fb_trace_ele of fb_trace_eles2) {
       const fb_text = await fb_trace_ele.getText();
       if (fb_text.includes('人在追蹤')) { // 經典版顯示方式
-          fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+        fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
         break;
       }
     }

diff --git a/ch16/tools/crawlerFB.js b/ch16/tools/crawlerFB.js
@@ -45,7 +45,7 @@ async function loginFacebook (driver) {
 
       //因為登入這件事情要等Server回應，你直接跳轉粉絲專頁會導致登入失敗
       //用登入後才有的元件，來判斷是否登入
-      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"oajrlxb2")]`)), long_time);
+      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"om3e55n1")]`)), long_time);
       return true;
     } catch (e) {
       console.error('FB登入失敗');
@@ -60,7 +60,7 @@ async function getTrace (driver, fan_page_name) {
   let is_accurate = true;//確認追蹤人數是否精準
   try {
     //因為考慮到每個粉專顯示追蹤人數的位置都不一樣，所以就採用全抓再分析
-    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"lrazzd5p")]`)), short_time);
+    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"g4qalytl")]`)), short_time);
     for (const fb_trace_ele of fb_trace_eles) {
       const fb_text = await fb_trace_ele.getText();
       if (fb_text.includes('位追蹤者')) { // 新版顯示方式
@@ -73,11 +73,13 @@ async function getTrace (driver, fan_page_name) {
         }
         break;
       } else if (fb_text.includes('個讚')) {
-        fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+        fb_trace = fb_text.
+          substr(0, fb_text.indexOf('個讚')). // 先移除後面字串
+          replace(/\D/g, ''); // 只取數字
       }
     }
     if (fb_trace === null) {
-      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"b1v8xokw")]`)), short_time);
+      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"pbevjfx6")]`)), short_time);
       for (const fb_trace_ele of fb_trace_eles2) {
         const fb_text = await fb_trace_ele.getText();
         if (fb_text.includes('人在追蹤')) { // 經典版顯示方式

diff --git a/ch17/tools/crawlerFB.js b/ch17/tools/crawlerFB.js
@@ -54,7 +54,7 @@ async function loginFacebook (driver) {
 
       //因為登入這件事情要等Server回應，你直接跳轉粉絲專頁會導致登入失敗
       //用登入後才有的元件，來判斷是否登入
-      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"oajrlxb2")]`)), long_time);
+      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"om3e55n1")]`)), long_time);
       return true;
     } catch (e) {
       console.error('FB登入失敗');
@@ -69,7 +69,7 @@ async function getTrace (driver, fan_page_name) {
   let is_accurate = true;//確認追蹤人數是否精準
   try {
     //因為考慮到每個粉專顯示追蹤人數的位置都不一樣，所以就採用全抓再分析
-    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"lrazzd5p")]`)), short_time);
+    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"g4qalytl")]`)), short_time);
     for (const fb_trace_ele of fb_trace_eles) {
       const fb_text = await fb_trace_ele.getText();
       if (fb_text.includes('位追蹤者')) { // 新版顯示方式
@@ -82,11 +82,13 @@ async function getTrace (driver, fan_page_name) {
         }
         break;
       } else if (fb_text.includes('個讚')) {
-        fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+        fb_trace = fb_text.
+          substr(0, fb_text.indexOf('個讚')). // 先移除後面字串
+          replace(/\D/g, ''); // 只取數字
       }
     }
     if (fb_trace === null) {
-      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"b1v8xokw")]`)), short_time);
+      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"pbevjfx6")]`)), short_time);
       for (const fb_trace_ele of fb_trace_eles2) {
         const fb_text = await fb_trace_ele.getText();
         if (fb_text.includes('人在追蹤')) { // 經典版顯示方式

diff --git a/ch18/tools/crawlerFB.js b/ch18/tools/crawlerFB.js
@@ -58,7 +58,7 @@ async function loginFacebook (driver) {
 
       //因為登入這件事情要等Server回應，你直接跳轉粉絲專頁會導致登入失敗
       //用登入後才有的元件，來判斷是否登入
-      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"oajrlxb2")]`)), long_time);
+      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"om3e55n1")]`)), long_time);
       return true;
     } catch (e) {
       console.error('FB登入失敗');
@@ -73,7 +73,7 @@ async function getTrace (driver, fan_page_name) {
   let is_accurate = true;//確認追蹤人數是否精準
   try {
     //因為考慮到每個粉專顯示追蹤人數的位置都不一樣，所以就採用全抓再分析
-    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"lrazzd5p")]`)), short_time);
+    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"g4qalytl")]`)), short_time);
     for (const fb_trace_ele of fb_trace_eles) {
       const fb_text = await fb_trace_ele.getText();
       if (fb_text.includes('位追蹤者')) { // 新版顯示方式
@@ -86,11 +86,13 @@ async function getTrace (driver, fan_page_name) {
         }
         break;
       } else if (fb_text.includes('個讚')) {
-        fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+        fb_trace = fb_text.
+          substr(0, fb_text.indexOf('個讚')). // 先移除後面字串
+          replace(/\D/g, ''); // 只取數字
       }
     }
     if (fb_trace === null) {
-      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"b1v8xokw")]`)), short_time);
+      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"pbevjfx6")]`)), short_time);
       for (const fb_trace_ele of fb_trace_eles2) {
         const fb_text = await fb_trace_ele.getText();
         if (fb_text.includes('人在追蹤')) { // 經典版顯示方式

diff --git a/ch19/tools/crawlerFB.js b/ch19/tools/crawlerFB.js
@@ -58,7 +58,7 @@ async function loginFacebook (driver) {
 
       //因為登入這件事情要等Server回應，你直接跳轉粉絲專頁會導致登入失敗
       //用登入後才有的元件，來判斷是否登入
-      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"oajrlxb2")]`)), long_time);
+      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"om3e55n1")]`)), long_time);
       return true;
     } catch (e) {
       console.error('FB登入失敗');
@@ -73,7 +73,7 @@ async function getTrace (driver, fan_page_name) {
   let is_accurate = true;//確認追蹤人數是否精準
   try {
     //因為考慮到每個粉專顯示追蹤人數的位置都不一樣，所以就採用全抓再分析
-    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"lrazzd5p")]`)), short_time);
+    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"g4qalytl")]`)), short_time);
     for (const fb_trace_ele of fb_trace_eles) {
       const fb_text = await fb_trace_ele.getText();
       if (fb_text.includes('位追蹤者')) { // 新版顯示方式
@@ -86,11 +86,13 @@ async function getTrace (driver, fan_page_name) {
         }
         break;
       } else if (fb_text.includes('個讚')) {
-        fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+        fb_trace = fb_text.
+          substr(0, fb_text.indexOf('個讚')). // 先移除後面字串
+          replace(/\D/g, ''); // 只取數字
       }
     }
     if (fb_trace === null) {
-      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"b1v8xokw")]`)), short_time);
+      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"pbevjfx6")]`)), short_time);
       for (const fb_trace_ele of fb_trace_eles2) {
         const fb_text = await fb_trace_ele.getText();
         if (fb_text.includes('人在追蹤')) { // 經典版顯示方式

diff --git a/ch21/tools/crawlerFB.js b/ch21/tools/crawlerFB.js
@@ -58,7 +58,7 @@ async function loginFacebook (driver) {
 
       //因為登入這件事情要等Server回應，你直接跳轉粉絲專頁會導致登入失敗
       //用登入後才有的元件，來判斷是否登入
-      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"oajrlxb2")]`)), long_time);
+      await driver.wait(until.elementLocated(By.xpath(`//*[contains(@class,"om3e55n1")]`)), long_time);
       return true;
     } catch (e) {
       console.error('FB登入失敗');
@@ -73,7 +73,7 @@ async function getTrace (driver, fan_page_name) {
   let is_accurate = true;//確認追蹤人數是否精準
   try {
     //因為考慮到每個粉專顯示追蹤人數的位置都不一樣，所以就採用全抓再分析
-    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"lrazzd5p")]`)), short_time);
+    const fb_trace_eles = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"g4qalytl")]`)), short_time);
     for (const fb_trace_ele of fb_trace_eles) {
       const fb_text = await fb_trace_ele.getText();
       if (fb_text.includes('位追蹤者')) { // 新版顯示方式
@@ -86,11 +86,13 @@ async function getTrace (driver, fan_page_name) {
         }
         break;
       } else if (fb_text.includes('個讚')) {
-        fb_trace = fb_text.replace(/\D/g, ''); // 只取數字
+        fb_trace = fb_text.
+          substr(0, fb_text.indexOf('個讚')). // 先移除後面字串
+          replace(/\D/g, ''); // 只取數字
       }
     }
     if (fb_trace === null) {
-      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"b1v8xokw")]`)), short_time);
+      const fb_trace_eles2 = await driver.wait(until.elementsLocated(By.xpath(`//*[contains(@class,"pbevjfx6")]`)), short_time);
       for (const fb_trace_ele of fb_trace_eles2) {
         const fb_text = await fb_trace_ele.getText();
         if (fb_text.includes('人在追蹤')) { // 經典版顯示方式