hamletbatista

#let's build a pandas dataframe with the search console data
import pandas as pd

def get_search_console_data(webproperty, days=-365):
  if webproperty is not None:
    query = webproperty.query.range(start='today', days=days).dimension('date', 'query')
    r = query.get()
    df = pd.DataFrame(r.rows)
    return df

hamletbatista

from requests_html import HTMLSession

#Builds a DOM path recursively
def build_dom_path(element, path):

  if element is None:
    return path
  else:
    path.append(element.tag)
  

hamletbatista

lxml
advertools
gitpython
PyYAML

hamletbatista

from git import Repo
from lxml import etree
import advertools as adv
from datetime import datetime
import yaml
import os

full_path="/tmp/wordpress-updates"

#get credentials from environment variables

hamletbatista

<title>Google Ads to Start Hiding Some Search Query Data</title>
<script type="application/ld+json">
    {
      "@context": "https://schema.org",
      "@type": "FAQPage",
      "mainEntity": [
    

    {
        "@type": "Question",

hamletbatista

class QueGenerator():
  def __init__(self):
    self.que_model = T5ForConditionalGeneration.from_pretrained('./t5_que_gen_model/t5_base_que_gen/')
    self.ans_model = T5ForConditionalGeneration.from_pretrained('./t5_ans_gen_model/t5_base_ans_gen/')

    self.que_tokenizer = T5Tokenizer.from_pretrained('./t5_que_gen_model/t5_base_tok_que_gen/')
    self.ans_tokenizer = T5Tokenizer.from_pretrained('./t5_ans_gen_model/t5_base_tok_ans_gen/')
    
    self.device = 'cuda' if torch.cuda.is_available() else 'cpu'
    

hamletbatista

from urllib.parse import urlparse
import re

url="https://www.amazon.com/SanDisk-128GB-microSDXC-Memory-Adapter/dp/B073JYC4XM/"

print(set(re.split("[/-]", urlparse(url).path)))

#output
#{'', 'B073JYC4XM', 'dp', '128GB', 'microSDXC', 'Memory', 'SanDisk', 'Adapter'}

hamletbatista

from glob import glob
import os
from collections import defaultdict
from pprint import pprint
import PIL

def detectnet_input():
    #images = glob(os.path.join(FLAGS.data_dir, '*.jpg'))
    exclude= ["page tabs", "original price", "product name0055-0922", "promotion text"]

hamletbatista

import cv2

def draw_bounding_boxes(file_path, prediction_result):

  ## read image file from disk
  img = cv2.imread(file_path, cv2.IMREAD_COLOR)
  
  height = img.shape[0] # Image height
  width = img.shape[1] # Image width

hamletbatista

import scrapy
import pickle

class ShopifyThemeLinkSpider(scrapy.Spider):

    name = 'shopifyspider'

    with open('theme_links.pkl', 'rb') as f:
      theme_links = pickle.load(f)