From ae9fb256c2eae24ac738edd76ab32744889e8906 Mon Sep 17 00:00:00 2001
From: YuJian <zhonghao@jobcn.com>
Date: Mon, 17 Jan 2022 11:32:25 +0800
Subject: [PATCH] =?UTF-8?q?=E5=8F=82=E6=95=B0=E9=94=99=E8=AF=AF?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 utils/saveImages.js |  4 ++--
 yitudao.js          | 16 +++++++++++-----
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/utils/saveImages.js b/utils/saveImages.js
index 7c4f53a..9e6a107 100644
--- a/utils/saveImages.js
+++ b/utils/saveImages.js
@@ -5,7 +5,7 @@ const fs = require("fs");
  * 图片下载
  * @param {*} imgObject 图片 URL
  */
-function saveImages(imgObject) {
+function saveImages(imgObject, total) {
   return new Promise((resolve, reject) => {
     const forItem = Object.keys(imgObject);
     for (let forItemIndex = 0; forItemIndex < forItem.length; forItemIndex++) {
@@ -15,7 +15,7 @@ function saveImages(imgObject) {
         else {
           const alreadyPath = fs.readdirSync(`./Result/${imTitle}`);
           // 已有文件跳过
-          if (alreadyPath.length === imgObject[imTitle].length) {
+          if (alreadyPath.length === total) {
             console.log(`${imTitle} 已存在 跳过抓取`);
             resolve()
             return;
diff --git a/yitudao.js b/yitudao.js
index 61f9409..8b71d68 100644
--- a/yitudao.js
+++ b/yitudao.js
@@ -36,7 +36,7 @@ urlArray = [
   "https://www.yitudao.com/meinv/rentiyishu/",
 ];
 
-let CURRY_PAGENUMBER = 1; // 爬取起始页码
+let CURRY_PAGENUMBER = 2; // 爬取起始页码
 let MAX_PAGENUMBER = 573; // 爬取最大页码
 
 // 爬取队列
@@ -56,7 +56,8 @@ const spiderQueue = async (soureUrl) => {
     for (let index = 0; index < requestQueue.length; index++) {
       console.log(
         `正在抓取第${CURRY_PAGENUMBER}页 ==>`,
-        requestQueue[index].title
+        requestQueue[index].title,
+        requestQueue[index].url
       );
       await loadHtml(requestQueue[index].url, requestQueue[index].title);
     }
@@ -74,15 +75,20 @@ const loadHtml = async (url, title) => {
     const $ = cheerio.load(data);
     const soureURL = url.substring(0, url.length - 5);
 
-    const forNum = $("#title .imageset-sum").html().slice(2);
+    const forNum = +$("#title .imageset-sum").html().slice(2);
 
     const loadQueue = [];
-    for (let index = 2; index <= forNum; index++) {
+    for (let index = 1; index <= forNum; index++) {
+      if (index === 1) {
+        const imageUrl = await loadImages(`${soureURL}.html`);
+        loadQueue.push(imageUrl);
+        continue;
+      }
       const imageUrl = await loadImages(`${soureURL}_${index}.html`);
       loadQueue.push(imageUrl);
     }
 
-    await saveImages({ [title]: loadQueue });
+    await saveImages({ [title]: loadQueue }, forNum);
   } catch (error) {
     console.log(`loadHtml: 下载${title}时出现错误！`);
     console.log(error);