eliasdabbas

import ipaddress

import requests
import pandas as pd

def bot_ip_addresses():
    bots_urls = {
        'google': 'https://developers.google.com/search/apis/ipranges/googlebot.json',
        'bing': 'https://www.bing.com/toolbox/bingbot.json'
    }

eliasdabbas

import networkx as nx
import pandas as pd

def score_links(links_file, domain):
    """Score a network on links based on their importance and centrality.

    links_file: Path to the file having the links (needs a "Source" and
                "Destination" columns) e.g. ScreamingFrog's outlinks file.
    domain: Filter all links, making sure they all point to the domain you want.
    """

eliasdabbas

# !pip install --upgrade transformers plotly pandas

import plotly.graph_objects as go
import pandas as pd
pd.options.display.max_columns = None
from transformers import pipeline
unmasker = pipeline('fill-mask', model='bert-base-uncased')

results = []
cars = ['mercedes', 'audi', 'bmw', 'volkswagen', 'ford', 'toyota',

eliasdabbas

from urllib.parse import urlsplit

import advertools as adv


sites = [
    'https://www.who.int',
    'https://www.nytimes.com',
    'https://www.washingtonpost.com',
]

eliasdabbas

import plotly.graph_objects as go
import pandas as pd

def serp_heatmap(df, num_domains=10, select_domain=None):
    df = df.rename(columns={'domain': 'displayLink',
                            'searchTerms': 'keyword'})
    top_domains = df['displayLink'].value_counts()[:num_domains].index.tolist()
    top_domains = df['displayLink'].value_counts()[:num_domains].index.tolist()
    top_df = df[df['displayLink'].isin(top_domains) & df['displayLink'].ne('')]