yanissi

{
    "name": "MagicEden Sales Bot v3 - Blueprint Provided by Deux à Trois (https://2a3.dev)",
    "flow": [
        {
            "id": 2,
            "module": "http:ActionSendData",
            "version": 3,
            "parameters": {
                "handleErrors": false,
                "useNewZLibDeCompress": true

yanissi

# Identify Unique Broken Links and Matches them to Original List of All External Links
def matchBrokenLinks(brokenLinksList,externalLinksListRaw):

    brokenLinkLocation = []

    for link in externalLinksListRaw:
        
        if link[1] in brokenLinksList:
                    
            brokenLinkLocation.append([link[0],link[1],link[2]])

yanissi

# Go through Each Unique Link to Identify Broken Ones
def identifyBrokenLinks(uniqueExternalLinks):

    count = 0
    length_uniqueExternalLinks = len(uniqueExternalLinks)
    
    user_agent = {'User-Agent': 'Mozilla/5.0 (X11; CrOS x86_64 8172.45.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.64 Safari/537.36'}

    brokenLinksList = []

yanissi

# Get External Links List RAW
def ExternalLinkList(listPages):

    externalLinksListRaw = []

    count = 0
    length_list = len(listPages)

    user_agent = {'User-Agent': 'Mozilla/5.0 (X11; CrOS x86_64 8172.45.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.64 Safari/537.36'}

yanissi

# Find and Parse Sitemaps to Create List of all website's pages
from usp.tree import sitemap_tree_for_homepage

def getPagesFromSitemap(fullDomain):

    listPagesRaw = []

    tree = sitemap_tree_for_homepage(fullDomain)
    for page in tree.all_pages():
        listPagesRaw.append(page.url)

yanissi

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():
    

yanissi

## Fixed Height Export

import requests
import urllib.request

token = "9HGDNG5-50E40Y9-MRTE5HC-HRWHPPB"
url = "https://www.dailymail.co.uk/news/article-9744405/Melbourne-best-city-working-home-Covid-losing-crown-liveable-city.html"

result = requests.get(f"https://shot.screenshotapi.net/screenshot?token={token}&url={url}&height=3000&output=json&no_cookie_banners=true&block_ads=true")

yanissi

## Fullpage Export

import requests
import urllib.request

token = "your_token_here"
url = "https://www.dailymail.co.uk/news/article-9744405/Melbourne-best-city-working-home-Covid-losing-crown-liveable-city.html"

result = requests.get(f"https://shot.screenshotapi.net/screenshot?token={token}&url={url}&full_page=1&output=json&no_cookie_banners=true&block_ads=true")

yanissi

import pandas as pd
import time
import re
from slugify import slugify

from html2image import Html2Image

hti = Html2Image()

df = pd.read_csv("clippings.csv")

yanissi

from html2image import Html2Image

hti = Html2Image()

hti.screenshot(url="https://martechwithme.com",save_as="screenshot.png").