Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update dependency version; Ignore pdf link to avoid crash #380

Open
wants to merge 7 commits into
base: master
Choose a base branch
from
Open

Update dependency version; Ignore pdf link to avoid crash #380

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
98b2b5b
Simply skip pdf files to avoid crash
mypchas6fans Jul 20, 2021
15f9014
Update puppeteer 4.0.1
mypchas6fans Jul 22, 2021
c948bfc
Update more dependencies
mypchas6fans Jul 22, 2021
290d7be
Update dev dependencies
mypchas6fans Jul 22, 2021
aaac5e0
Update yarn.lock
mypchas6fans Jul 22, 2021
290c9d3
update to puppeteer 10.1.0
Jul 22, 2021
4ae12b7
Print console log optionally
mypchas6fans Nov 11, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
5 changes: 3 additions & 2 deletions lib/crawler.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ const reduce = require('lodash/reduce');
const pick = require('lodash/pick');
const isEmpty = require('lodash/isEmpty');
const uniq = require('lodash/uniq');
const devices = require('puppeteer/DeviceDescriptors');
const devices = require('puppeteer').devices;
const {
resolveUrl,
debugConsole,
Expand Down Expand Up @@ -199,7 +199,8 @@ class Crawler {
*/
_handlePageEvents() {
this._page.on('pageerror', text => void debugConsole(text));
this._page.on('console', msg => void debugConsole(`${msg.type()} ${msg.text()} at ${this._options.url}`));
//this._page.on('console', msg => void debugConsole(`${msg.type()} ${msg.text()} at ${this._options.url}`));
//this._page.on('console', msg => console.log(`${msg.type()} ${msg.text()} at ${this._options.url}`));
this._page.on('dialog', dialog => void this._handleDialog(dialog));
}

Expand Down
2 changes: 1 addition & 1 deletion lib/hccrawler.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ const rp = require('request-promise');
// @ts-ignore
const robotsParser = require('robots-parser');
const Puppeteer = require('puppeteer');
const devices = require('puppeteer/DeviceDescriptors');
const devices = require('puppeteer').devices;
const {
delay,
generateKey,
Expand Down
3 changes: 3 additions & 0 deletions lib/helper.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ const crypto = require('crypto');
const pick = require('lodash/pick');
const trim = require('lodash/trim');
const startsWith = require('lodash/startsWith');
const endsWith = require('lodash/endsWith');
const some = require('lodash/some');
const includes = require('lodash/includes');
const isPlainObject = require('lodash/isPlainObject');
Expand Down Expand Up @@ -73,6 +74,8 @@ class Helper {
url = trim(url);
if (!url) return null;
if (startsWith(url, '#')) return null;
if (endsWith(url, '.pdf')) return null;

const { protocol } = parse(url);
if (includes(['http:', 'https:'], protocol)) {
return url.split('#')[0];
Expand Down
42 changes: 21 additions & 21 deletions package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,34 +25,34 @@
},
"homepage": "https://github.com/yujiosaka/headless-chrome-crawler#readme",
"dependencies": {
"debug": "3.1.0",
"jquery": "3.5.1",
"lodash": "4.17.20",
"puppeteer": "1.20.0",
"debug": "4.3.2",
"jquery": "3.6.0",
"lodash": "4.17.21",
"puppeteer": "10.1.0",
"request": "2.88.2",
"request-promise": "4.2.6",
"robots-parser": "1.0.2"
"robots-parser": "2.3.0"
},
"peerDependencies": {
"redis": "2.8.0"
"redis": "3.1.2"
},
"devDependencies": {
"@commitlint/cli": "7.0.0",
"@commitlint/config-conventional": "7.0.0",
"@types/debug": "0.0.30",
"@types/lodash": "4.14.162",
"@types/node": "10.3.4",
"@types/puppeteer": "1.20.0",
"@types/request-promise": "4.1.46",
"eslint": "5.0.1",
"eslint-config-airbnb": "17.0.0",
"eslint-plugin-import": "2.13.0",
"@commitlint/cli": "12.1.4",
"@commitlint/config-conventional": "12.1.4",
"@types/debug": "4.1.6",
"@types/lodash": "4.14.171",
"@types/node": "14.17.3",
"@types/puppeteer": "5.4.4",
"@types/request-promise": "4.1.48",
"eslint": "7.31.0",
"eslint-config-airbnb": "18.2.1",
"eslint-plugin-import": "2.23.4",
"greenkeeper-lockfile": "1.15.1",
"husky": "0.14.3",
"jest": "23.1.0",
"mime": "2.3.0",
"redis": "2.8.0",
"typescript": "2.7.2"
"husky": "7.0.1",
"jest": "27.0.6",
"mime": "2.5.2",
"redis": "3.1.2",
"typescript": "4.3.5"
},
"keywords": [
"headless",
Expand Down