Bypassing Cloudflare protection for Scraping
Bypassing Cloudflare protection for Scraping
Starting a Browser.
google-chrome --remote-debugging-port=9222 --no-first-run --no-default-browser-check --disable-default-apps --user-data-dir=./browser-data-tmp/
[
"google-chrome",
"--remote-debugging-port=9222",
"--no-first-run",
" --no-default-browser-check",
"--disable-default-apps",
"--user-data-dir=./browser-data-tmp/",
]
Scraping Steps.
[
{
"id": 1,
"method": "Emulation.setDeviceMetricsOverride",
"params": {
"width": 800,
"height": 800,
"deviceScaleFactor": 1,
"mobile": false
}
},
{
"id": 2,
"method": "Page.navigate",
"params": {
"url": "https://www.scrapingcourse.com/"
}
},
{
"id": 2,
"method": "Page.navigate",
"params": {
"url": "https://www.scrapingcourse.com/cloudflare-challenge"
}
},
{
"id": 4,
"method": "Input.dispatchMouseEvent",
"params": {
"type": "mousePressed",
"x": 45,
"y": 290,
"button": "left",
"clickCount": 1
}
},
{
"id": 5,
"method": "Input.dispatchMouseEvent",
"params": {
"type": "mouseReleased",
"x": 45,
"y": 290,
"button": "left",
"clickCount": 1
}
},
{
"id": 5,
"method": "DOM.getDocument",
"params": {
"depth": -1
}
},
{
"id": 6,
"method": "DOM.getOuterHTML",
"params": {
"nodeId": 3
}
}
]