{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## 1a. A demo of using pandas to bulk download files...\n", "Building off the method we just looked at of using Pandas to grab a single file, we see here how Python can be quite effective at downloading industrial water data for **all** US states. \n", "\n", "Compare running this script with doing the downloads by hand..." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "#import os, us and pandas\n", "import os, us\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "#Create a folder to hold all the downloads\n", "outFolder = \"WaterData\"\n", "if not os.path.exists(outFolder): os.mkdir(outFolder)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "#Loop through each state, download it's data, and save to a local file\n", "for state in us.STATES:\n", " stateAbbr = state.abbr.lower()\n", " print(\"{}\".format(stateAbbr),end='>')\n", " \n", " #Update the url with the state code\n", " theURL = 'https://waterdata.usgs.gov/{}/nwis/water_use?format=rdb&rdb_compression=value&wu_area=County&wu_year=ALL&wu_county=ALL&wu_category=IN&wu_county_nms=--ALL%2BCounties--&wu_category_nms=Industrial'\n", " theURL = theURL.format(stateAbbr)\n", " \n", " #Get the data as a dataframe\n", " dfState = pd.read_csv(theURL,delimiter='\\t',skiprows=list(range(49))+[50])\n", " \n", " #write df to csv in the WaterData folder\n", " dfState.to_csv(\"WaterData/{}.csv\".format(stateAbbr),index=False)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 2 }