ajitmp

name: Continuous Integration and Delivery

on: [push]

env:
  #
  DJANGO_TUTORIAL_API_IMAGE: ghcr.io/$(echo $GITHUB_REPOSITORY | tr '[:upper:]' '[:lower:]')/store
  DJANGO_TUTORIAL_NGINX_IMAGE: ghcr.io/$(echo $GITHUB_REPOSITORY | tr '[:upper:]' '[:lower:]')/nginx
  REGISTRY: ghcr.io

ajitmp

import json
from pydantic import BaseModel, ValidationError
from ajit_utils import list_of_dict_to_json


# Define the Pydantic data class (model)
class Person(BaseModel):
    name: str
    age: int
    city: str = "Unknown"  # Default value

ajitmp

import json

def list_of_dict_to_json(list_data_dict:list, filename:str)-> None:
    """This is a utiltiy method to write python dictonary data
    to a json file.

    Args:
        list_data_dict (list): Python list of dict having the data
        filename (str): Filename for the json file
    example_data = [

ajitmp

[
  {
    "id": 1,
    "title": "Python Programming for Beginners",
    "author": "John Smith",
    "price": 29.99
  },
  {
    "id": 2,
    "title": "JavaScript: The Good Parts",

ajitmp

[
  {
    "title": "Example Book 1",
    "author": "John Doe",
    "isbn": "1234567890123",
    "pages": 350,
    "language": "English"
  },
  {
    "title": "Example Book 2",

ajitmp

[
  {
    "spidername": "Quote Ajit Source",
    "start_urls": ["https://quotes-scrape.netlify.app/"],
    "quote_div_main": "div.quote-container",
    "title_selector": "h2.title",
    "author_selector": "p.author"
  },
  {
    "spidername": "Brainy Quote",

ajitmp

import json
from jinja2 import Environment, FileSystemLoader
from urllib.parse import urlparse
import os

# Load JSON configuration
with open('sources.json') as f:
    sources = json.load(f)

# Set up Jinja2 environment

ajitmp

import scrapy
from spiders_automation_demo.items import QuoteItem
from spiders_automation_demo.itemsloader import QuoteLoader

class {{ spiderclass}}(scrapy.Spider):
    name = "{{spidername}}"
    allowed_domains = ["{{allowed_domains}}"]
    start_urls = {{start_urls}}

    def parse(self, response):

ajitmp

ITEM_PIPELINES = {
    'spiders_automation_demo.pipelines.FilterQuotesPipelineLoveOrLife': 300,
}

ajitmp

from scrapy.exceptions import DropItem

class FilterQuotesPipelineLoveOrLife:
    def process_item(self, item, spider):
        # Check if 'love' or 'life' is in the text
        if 'love' in item['title'].lower() or 'life' in item['title'].lower():
            return item
        else:
            raise DropItem(f"Quote without 'love' or 'life' in title text: {item['title']}")