Skip to content

Instantly share code, notes, and snippets.

@yanissi
Created August 4, 2021 17:35
Show Gist options
  • Save yanissi/d2d6345561b8851a139703752be8d847 to your computer and use it in GitHub Desktop.
Save yanissi/d2d6345561b8851a139703752be8d847 to your computer and use it in GitHub Desktop.
import requests
import pandas as pd
import urllib.request
from slugify import slugify
df = pd.read_csv("clippings.csv")
token = "9HGDNG5-50E40Y9-MRTE5HC-HRWHPPB"
for clipping in df.itertuples():
try:
clippingUrl = clipping[1]
print(f"Trying {clippingUrl} Full Page")
fileName = slugify(clippingUrl).replace("-html","").replace("www-","").replace("https-","")
result = requests.get(f"https://shot.screenshotapi.net/screenshot?token={token}&url={clippingUrl}&full_page=1&output=json&no_cookie_banners=true&block_ads=true")
urllib.request.urlretrieve(result.json()['screenshot'], f"{fileName}.png")
print(clippingUrl + " Done")
except:
try:
print(f"Trying {clippingUrl} 3000 height")
fileName = slugify(clippingUrl).replace("-html","").replace("www-","").replace("https-","")
result = requests.get(f"https://shot.screenshotapi.net/screenshot?token={token}&url={clippingUrl}&height=3000&output=json&no_cookie_banners=true&block_ads=true")
urllib.request.urlretrieve(result.json()['screenshot'], f"{fileName}.png")
print(clippingUrl + " Done")
except:
try:
print(f"Trying {clippingUrl} 1000 height")
fileName = slugify(clipping).replace("-html","").replace("www-","").replace("https-","")
result = requests.get(f"https://shot.screenshotapi.net/screenshot?token={token}&url={clippingUrl}&height=1000&output=json&no_cookie_banners=true&block_ads=true")
urllib.request.urlretrieve(result.json()['screenshot'], f"{fileName}.png")
print(clippingUrl + " Done")
except:
print(f"Failed: {clippingUrl}")
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment