"""
.. _download_gdelt_climate_en:
"""
import os
import requests
import zipfile
import logging
from dotenv import find_dotenv, load_dotenv
from arg_mine import PROJECT_DIR
from arg_mine.utils import LOG_FMT, get_logger
_logger = get_logger(__name__, logging.DEBUG)
# URL taken from https://blog.gdeltproject.org/a-new-contextual-dataset-for-exploring-climate-change-narratives-6-3m-english-news-urls-with-contextual-snippets-2015-2020/ # noqa: E501
BASE_URL_FMT = "http://data.gdeltproject.org/blog/2020-climate-change-narrative/WebNewsEnglishSnippets.{year}.csv.zip"
def download_file_from_url(url, target_file_path):
"""
Download a file from the given url
Parameters
----------
url : str
target URL to download file from
target_file_path : str
path to download the file to
Returns
"""
Main entry point for document sentence argument classification from a list of URLs
TODO: add unit testing for the CLI options
"""
import os
import logging
import click
from arg_mine import DATA_DIR
from arg_mine.data.loaders import get_gdelt_df
from arg_mine.api import classify
from arg_mine import utils
_logger = utils.get_logger(__name__, logging.DEBUG)
# formatted string template for the output filenames
_WRITE_FILENAME_FMT = "gdelt_{year}_{data}_docs{start:0{ndigit}d}-{end:0{ndigit}d}.csv"
@click.command()
@click.option(
"--ndocs",
default=100,
type=int,
help="The number of documents we want to extract from the list",
)
@click.option(
"--start-row",
default=0,
type=int,