木偶不认识的链接
我试图抢在表达一些HTML，但不知何故，我得到错误
Error: Evaluation failed: ReferenceError: link is not defined
at __puppeteer_evaluation_script__:8:29
at ExecutionContext.evaluateHandle (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\ExecutionContext.js:124:13)
at process._tickCallback (internal/process/next_tick.js:68:7)
-- ASYNC --
at ExecutionContext.<anonymous> (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\helper.js:144:27)
at ExecutionContext.evaluate (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\ExecutionContext.js:58:31)
at ExecutionContext.<anonymous> (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\helper.js:145:23)
at Frame.evaluate (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\FrameManager.js:447:20)
at process._tickCallback (internal/process/next_tick.js:68:7)
-- ASYNC --
at Frame.<anonymous> (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\helper.js:144:27)
at Page.evaluate (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\Page.js:777:43)
at Page.<anonymous> (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\helper.js:145:23)
at zrGrabber.StartGrabbingHtml (C:\Repositories\auto-grabber-server\grabbers\zr.grabber.js:52:40)
at process._tickCallback (internal/process/next_tick.js:68:7)
链接已被传递到StartGrabbingHtml功能，但随后我，m到处提到的错误。我想，什么是错与异步的工作人员，但不能得到究竟是什么。
const puppeteer = require("puppeteer");
let links = [];
const Mongo = require('./../db/mongo');
const zrLinks = [
"/",
"/",
"/"
];
module.exports = class zrGrabber {
async startGrabbingLinks() {
try {
for (let i = 0; i < zrLinks.length; i++) {
const browser = await puppeteer.launch();
const page = await browser.newPage();
await page.goto(zrLinks[i], {
waitUntil: 'load',
timeout: 0
});
const result = await page.evaluate(() => {
const links = document.querySelectorAll('div.head > h2 > a')
return [...links].map(link => link.href);
});
await page.close();
await browser.close();
links = [...links, ...result];
}
const db = new Mongo();
for (let i = 0; i < links.length; i++) {
// if link already in database skip grabbing
const found = await db.findLink(links[i]);
if (found) {
continue;
}
// else grab and write link to database
await this.StartGrabbingHtml(links[i])
}
} catch (err) {
console.log(err)
}
}
async StartGrabbingHtml(link) {
try {
const browser = await puppeteer.launch();
const page = await browser.newPage();
await page.goto(link, {
waitUntil: 'load',
timeout: 0
});
const article = await page.evaluate(() => { // error throwing here
const date = document.querySelector('#storyDetailArticle > time').innerHTML;
const name = document.querySelector('#storyDetailArticle > h1').innerHTML;
const description = document.querySelector('#storyDetailArticle > div.stroy_announcement > h3').innerHTML;
const author = document.querySelector('#storyDetailArticle > div.announcement_author.story_author.no_preview > div').innerHTML;
const content = document.querySelector('#storyDetailArticle > div.stroy_content').innerHTML;
return {
source: link,
date: date,
name: name,
description: description,
author: author,
content: content
};
});
console.log(article)
const db = new Mongo();
await db.insertOne(article);
await page.close();
await browser.close();
} catch (err) {
console.log(err)
}
}
}
什么我做错了吗？
回答如下：该脚本不能从link上下文中访问变量page.evaluate。
你应该把它作为像这样的说法：
await page.evaluate(link => {
// ...
}, link);
木偶不认识的链接
我试图抢在表达一些HTML，但不知何故，我得到错误
Error: Evaluation failed: ReferenceError: link is not defined
at __puppeteer_evaluation_script__:8:29
at ExecutionContext.evaluateHandle (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\ExecutionContext.js:124:13)
at process._tickCallback (internal/process/next_tick.js:68:7)
-- ASYNC --
at ExecutionContext.<anonymous> (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\helper.js:144:27)
at ExecutionContext.evaluate (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\ExecutionContext.js:58:31)
at ExecutionContext.<anonymous> (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\helper.js:145:23)
at Frame.evaluate (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\FrameManager.js:447:20)
at process._tickCallback (internal/process/next_tick.js:68:7)
-- ASYNC --
at Frame.<anonymous> (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\helper.js:144:27)
at Page.evaluate (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\Page.js:777:43)
at Page.<anonymous> (C:\Repositories\auto-grabber-server\node_modules\puppeteer\lib\helper.js:145:23)
at zrGrabber.StartGrabbingHtml (C:\Repositories\auto-grabber-server\grabbers\zr.grabber.js:52:40)
at process._tickCallback (internal/process/next_tick.js:68:7)
链接已被传递到StartGrabbingHtml功能，但随后我，m到处提到的错误。我想，什么是错与异步的工作人员，但不能得到究竟是什么。
const puppeteer = require("puppeteer");
let links = [];
const Mongo = require('./../db/mongo');
const zrLinks = [
"/",
"/",
"/"
];
module.exports = class zrGrabber {
async startGrabbingLinks() {
try {
for (let i = 0; i < zrLinks.length; i++) {
const browser = await puppeteer.launch();
const page = await browser.newPage();
await page.goto(zrLinks[i], {
waitUntil: 'load',
timeout: 0
});
const result = await page.evaluate(() => {
const links = document.querySelectorAll('div.head > h2 > a')
return [...links].map(link => link.href);
});
await page.close();
await browser.close();
links = [...links, ...result];
}
const db = new Mongo();
for (let i = 0; i < links.length; i++) {
// if link already in database skip grabbing
const found = await db.findLink(links[i]);
if (found) {
continue;
}
// else grab and write link to database
await this.StartGrabbingHtml(links[i])
}
} catch (err) {
console.log(err)
}
}
async StartGrabbingHtml(link) {
try {
const browser = await puppeteer.launch();
const page = await browser.newPage();
await page.goto(link, {
waitUntil: 'load',
timeout: 0
});
const article = await page.evaluate(() => { // error throwing here
const date = document.querySelector('#storyDetailArticle > time').innerHTML;
const name = document.querySelector('#storyDetailArticle > h1').innerHTML;
const description = document.querySelector('#storyDetailArticle > div.stroy_announcement > h3').innerHTML;
const author = document.querySelector('#storyDetailArticle > div.announcement_author.story_author.no_preview > div').innerHTML;
const content = document.querySelector('#storyDetailArticle > div.stroy_content').innerHTML;
return {
source: link,
date: date,
name: name,
description: description,
author: author,
content: content
};
});
console.log(article)
const db = new Mongo();
await db.insertOne(article);
await page.close();
await browser.close();
} catch (err) {
console.log(err)
}
}
}
什么我做错了吗？
回答如下：该脚本不能从link上下文中访问变量page.evaluate。
你应该把它作为像这样的说法：
await page.evaluate(link => {
// ...
}, link);