{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true }, "outputs": [], "source": [ "from webarchiv import WebarchivSession\n", "apikey = '2pm8i0hnmpcTK4Oj4CUeBoZd7vywrm4c'\n", "w = WebarchivSession(apikey)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Submit a fulltext search to get a list of tophits per domain ordered by the largest number of hits" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "response = w.fulltext_search(\"Nationalbibliothek Prunksaal Schwarzenegger\")\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The search always returns the full response. Checking for status_code 200 before extracting the response is always a good idea" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "if response.status_code != 200:\n", " print(\"Something went wrong ...\")\n", " exit(1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now it is safe to extract the response" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Get the tophit of the domain with the largest number of hits which contains the words Nationalbliothek, Prunksaal and Schwarzenegger" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "http://www.onb.ac.at/services/21696.htm\n" ] } ], "source": [ "print (response.json()['hits'][0]['value'])\n" ] } ], "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": 1 }