Created
March 1, 2021 03:15
-
-
Save datadavev/120414effb6d785f5bfdfa9fc5a82eca to your computer and use it in GitHub Desktop.
server caching and ld
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "id": "similar-train", | |
| "metadata": {}, | |
| "source": [ | |
| "Two requests are sent to the same URL using technically the same Accept header, though it differs literally.\n", | |
| "\n", | |
| "In the first instance, a response of `application/ld+json` is received. In the second a response of `text/html` is received." | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 1, | |
| "id": "devoted-intent", | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "import requests\n", | |
| "\n", | |
| "interest = ['Cache-Control', 'Content-Type', 'Content-Length', 'Location', 'X-Drupal-Cache']\n", | |
| "\n", | |
| "def loghistory(resp):\n", | |
| " print(f\"Req headers: {resp.request.headers}\")\n", | |
| " def ph(_id, _h):\n", | |
| " print(f\"{i}: URL: {_h.url}\")\n", | |
| " print(f\" Status: {_h.status_code}\")\n", | |
| " print(\" headers:\")\n", | |
| " for hk in sorted(_h.headers):\n", | |
| " if hk in interest:\n", | |
| " print(f\" {hk} : {_h.headers[hk]}\")\n", | |
| "\n", | |
| " i = 0\n", | |
| " for h in resp.history:\n", | |
| " ph(i, h)\n", | |
| " i = i+1\n", | |
| " ph(i, resp)\n", | |
| " " | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "id": "occupational-dealing", | |
| "metadata": {}, | |
| "source": [ | |
| "Send a request asking specifically for a JSON-LD response:" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 2, | |
| "id": "planned-method", | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Req headers: {'User-Agent': 'python-requests/2.25.1', 'Accept-Encoding': 'gzip, deflate', 'Accept': 'application/ld+json', 'Connection': 'keep-alive'}\n", | |
| "0: URL: https://www.bco-dmo.org/dataset/3160\n", | |
| " Status: 301\n", | |
| " headers:\n", | |
| " Cache-Control : no-cache, must-revalidate\n", | |
| " Content-Length : 20\n", | |
| " Content-Type : text/html; charset=UTF-8\n", | |
| " Location : https://www.bco-dmo.org/node/3160.jsonld\n", | |
| " X-Drupal-Cache : MISS\n", | |
| "1: URL: https://www.bco-dmo.org/node/3160.jsonld\n", | |
| " Status: 301\n", | |
| " headers:\n", | |
| " Cache-Control : no-cache, must-revalidate\n", | |
| " Content-Length : 20\n", | |
| " Content-Type : text/html; charset=UTF-8\n", | |
| " Location : https://www.bco-dmo.org/node/3160/rdf/jsonld\n", | |
| " X-Drupal-Cache : MISS\n", | |
| "2: URL: https://www.bco-dmo.org/node/3160/rdf/jsonld\n", | |
| " Status: 200\n", | |
| " headers:\n", | |
| " Cache-Control : public, max-age=900\n", | |
| " Content-Length : 2635\n", | |
| " Content-Type : application/ld+json\n", | |
| " X-Drupal-Cache : MISS\n", | |
| "{\"@context\":{\"content\":\"http:\\/\\/purl.org\\/rss\\/1.0\\/modules\\/content\\/\",\"dc\":\"http:\\/\\/purl.org\\/dc\\/terms\\/\",\"foaf\":\"http:\\/\\/xmlns.com\\/foaf\\/0.1\\/\",\"og\":\"http:\\/\\/ogp.me\\/ns#\",\"rdfs\":\"http:\\/\\/www.w3.org\\/2000\\/01\\/rdf-schema#\",\"sioc\":\"http:\\/\\/rdfs.org\\/sioc\\/ns#\",\"sioct\":\"http:\\/\\/rdfs.org\\/sioc\\/types#\",\"skos\":\"http:\\/\\/www.w3.org\\/2004\\/02\\/skos\\/core#\",\"xsd\":\"http:\\/\\/www.w3.org\\/2001\\/XMLSchema#\",\"owl\":\"http:\\/\\/www.w3.org\\/2002\\/07\\/owl#\",\"rdf\":\"http:\\/\\/www.w3.org\\/1999\\/02\\/22-rdf-syntax-ns#\",\"rss\":\"http:\\/\\/purl.org\\/rss\\/1.0\\/\",\"site\":\"https:\\/\\/www.bco-dmo.org\\/ns#\",\"odo\":\"http:\\/\\/ocean-data.org\\/schema\\/\",\"emo\":\"http:\\/\\/ocean-data.org\\/schema\\/entity-matching#\",\"bibo\":\"http:\\/\\/purl.org\\/ontology\\/bibo\\/\",\"crypto\":\"http:\\/\\/id.loc.gov\\/vocabulary\\/preservation\\/cryptographicHashFunctions\\/\",\"bcodmo\":\"http:\\/\\/lod.bco-dmo.org\\/id\\/\",\"arpfo\":\"http:\\/\\/vocab.ox.ac.uk\\/projectfunding#\",\"tw\":\"http:\\/\\/tw.rpi.edu\\/schema\\/\",\"dcat\":\"http:\\/\\/www.w3.org\\/ns\\/dcat#\",\"time\":\"http:\\/\\/www.w3.org\\/2006\\/time#\",\"geo\":\"http:\\/\\/www.w3.org\\/2003\\/01\\/geo\\/wgs84_pos#\",\"geosparql\":\"http:\\/\\/www.opengis.net\\/ont\\/geosparql#\",\"sf\":\"http:\\/\\/www.opengis.net\\/ont\\/sf#\",\"void\":\"http:\\/\\/rdfs.org\\/ns\\/void#\",\"sd\":\"http:\\/\\/www.w3.org\\/ns\\/sparql-service-description#\",\"dctype\":\"http:\\/\\/purl.org\\/dc\\/dcmitype\\/\",\"prov\":\"http:\\/\\/www.w3.org\\/ns\\/prov#\",\"schema\":\"http:\\/\\/schema.org\\/\",\"geolink\":\"http:\\/\\/schema.geolink.org\\/1.0\\/base\\/main#\"},\"@id\":\"http:\\/\\/lod.bco-dmo.org\\/id\\/dataset\\/3160#graph\",\"@graph\":[{\"http:\\/\\/lod.bco-dmo.org\\/id\\/dataset\\/3160\":{\"@id\":\"http:\\/\\/lod.bco-dmo.org\\/id\\/dataset\\/3160\",\"@type\":[\"http:\\/\\/ocean-data.org\\/schema\\/DeploymentDatasetCollection\",\"http:\\/\\/www.w3.org\\/ns\\/dcat#Dataset\",\"http:\\/\\/www.w3.org\\/ns\\/prov#Entity\",\"http:\\/\\/ocean-data.org\\/schema\\/Dataset\"],\"http:\\/\\/ocean-data.org\\/schema\\/hasAcquisitionDescription\":[{\"@value\":\"<div xmlns=\\\"http:\\/\\/www.w3.org\\/1999\\/xhtml\\\" lang=\\\"en\\\"><p>Generated by BCO-DMO staff from project \n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "url = \"https://www.bco-dmo.org/dataset/3160\"\n", | |
| "headers = {\"Accept\":\"application/ld+json\"}\n", | |
| "response1 = requests.get(url, headers=headers, timeout=30)\n", | |
| "loghistory(response1)\n", | |
| "#print the first 2k chars\n", | |
| "print(response1.text[:2000])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "id": "concrete-illness", | |
| "metadata": {}, | |
| "source": [ | |
| "Send another request to the same URL requesting the same, except using prioritization of formats in the Accept header:" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 3, | |
| "id": "constitutional-heaven", | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Req headers: {'User-Agent': 'python-requests/2.25.1', 'Accept-Encoding': 'gzip, deflate', 'Accept': 'application/ld+json;q=1.0,text/html;q=0.8', 'Connection': 'keep-alive'}\n", | |
| "0: URL: https://www.bco-dmo.org/dataset/3160\n", | |
| " Status: 200\n", | |
| " headers:\n", | |
| " Cache-Control : public, max-age=900\n", | |
| " Content-Type : text/html; charset=utf-8\n", | |
| " X-Drupal-Cache : MISS\n", | |
| "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML+RDFa 1.0//EN\"\n", | |
| " \"http://www.w3.org/MarkUp/DTD/xhtml-rdfa-1.dtd\">\n", | |
| "<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" version=\"XHTML+RDFa 1.0\" dir=\"ltr\"\n", | |
| " xmlns:content=\"http://purl.org/rss/1.0/modules/content/\"\n", | |
| " xmlns:dc=\"http://purl.org/dc/terms/\"\n", | |
| " xmlns:foaf=\"http://xmlns.com/foaf/0.1/\"\n", | |
| " xmlns:og=\"http://ogp.me/ns#\"\n", | |
| " xmlns:rdfs=\"http://www.w3.org/2000/01/rdf-schema#\"\n", | |
| " xmlns:sioc=\"http://rdfs.org/sioc/ns#\"\n", | |
| " xmlns:sioct=\"http://rdfs.org/sioc/types#\"\n", | |
| " xmlns:skos=\"http://www.w3.org/2004/02/skos/core#\"\n", | |
| " xmlns:xsd=\"http://www.w3.org/2001/XMLSchema#\"\n", | |
| " xmlns:owl=\"http://www.w3.org/2002/07/owl#\"\n", | |
| " xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\"\n", | |
| " xmlns:rss=\"http://purl.org/rss/1.0/\"\n", | |
| " xmlns:site=\"https://www.bco-dmo.org/ns#\"\n", | |
| " xmlns:odo=\"http://ocean-data.org/schema/\"\n", | |
| " xmlns:emo=\"http://ocean-data.org/schema/entity-matching#\"\n", | |
| " xmlns:bibo=\"http://purl.org/ontology/bibo/\"\n", | |
| " xmlns:crypto=\"http://id.loc.gov/vocabulary/preservation/cryptographicHashFunctions/\"\n", | |
| " xmlns:bcodmo=\"http://lod.bco-dmo.org/id/\"\n", | |
| " xmlns:arpfo=\"http://vocab.ox.ac.uk/projectfunding#\"\n", | |
| " xmlns:tw=\"http://tw.rpi.edu/schema/\"\n", | |
| " xmlns:dcat=\"http://www.w3.org/ns/dcat#\"\n", | |
| " xmlns:time=\"http://www.w3.org/2006/time#\"\n", | |
| " xmlns:geo=\"http://www.w3.org/2003/01/geo/wgs84_pos#\"\n", | |
| " xmlns:geosparql=\"http://www.opengis.net/ont/geosparql#\"\n", | |
| " xmlns:sf=\"http://www.opengis.net/ont/sf#\"\n", | |
| " xmlns:void=\"http://rdfs.org/ns/void#\"\n", | |
| " xmlns:sd=\"http://www.w3.org/ns/sparql-service-description#\"\n", | |
| " xmlns:dctype=\"http://purl.org/dc/dcmitype/\"\n", | |
| " xmlns:prov=\"http://www.w3.org/ns/prov#\"\n", | |
| " xmlns:schema=\"http://schema.org/\"\n", | |
| " xmlns:geolink=\"http://schema.geolink.org/1.0/base/main#\">\n", | |
| "\n", | |
| "<head profile=\"http://www.w3.org/1999/xhtml/vocab\">\n", | |
| " <meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n", | |
| "<meta name=\"Generator\" content=\"Drupal 7 (http://drupal.org)\" />\n", | |
| "<link rel=\"canonical\" href=\"https://www.bco-dmo.org/dataset/3160\" />\n", | |
| "<link rel=\"shortlink\" href=\"/node/3160\" />\n", | |
| "<scr\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "url = \"https://www.bco-dmo.org/dataset/3160\"\n", | |
| "headers = {\"Accept\":\"application/ld+json;q=1.0,text/html;q=0.8\"}\n", | |
| "response2 = requests.get(url, headers=headers, timeout=30)\n", | |
| "loghistory(response2)\n", | |
| "#print the first 2k chars\n", | |
| "print(response2.text[:2000])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 4, | |
| "id": "sensitive-parker", | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Req headers: {'User-Agent': 'python-requests/2.25.1', 'Accept-Encoding': 'gzip, deflate', 'Accept': 'application/ld+json', 'Connection': 'keep-alive'}\n", | |
| "0: URL: https://www.bco-dmo.org/dataset/3160\n", | |
| " Status: 200\n", | |
| " headers:\n", | |
| " Cache-Control : public, max-age=900\n", | |
| " Content-Type : text/html; charset=utf-8\n", | |
| " X-Drupal-Cache : HIT\n", | |
| "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML+RDFa 1.0//EN\"\n", | |
| " \"http://www.w3.org/MarkUp/DTD/xhtml-rdfa-1.dtd\">\n", | |
| "<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" version=\"XHTML+RDFa 1.0\" dir=\"ltr\"\n", | |
| " xmlns:content=\"http://purl.org/rss/1.0/modules/content/\"\n", | |
| " xmlns:dc=\"http://purl.org/dc/terms/\"\n", | |
| " xmlns:foaf=\"http://xmlns.com/foaf/0.1/\"\n", | |
| " xmlns:og=\"http://ogp.me/ns#\"\n", | |
| " xmlns:rdfs=\"http://www.w3.org/2000/01/rdf-schema#\"\n", | |
| " xmlns:sioc=\"http://rdfs.org/sioc/ns#\"\n", | |
| " xmlns:sioct=\"http://rdfs.org/sioc/types#\"\n", | |
| " xmlns:skos=\"http://www.w3.org/2004/02/skos/core#\"\n", | |
| " xmlns:xsd=\"http://www.w3.org/2001/XMLSchema#\"\n", | |
| " xmlns:owl=\"http://www.w3.org/2002/07/owl#\"\n", | |
| " xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\"\n", | |
| " xmlns:rss=\"http://purl.org/rss/1.0/\"\n", | |
| " xmlns:site=\"https://www.bco-dmo.org/ns#\"\n", | |
| " xmlns:odo=\"http://ocean-data.org/schema/\"\n", | |
| " xmlns:emo=\"http://ocean-data.org/schema/entity-matching#\"\n", | |
| " xmlns:bibo=\"http://purl.org/ontology/bibo/\"\n", | |
| " xmlns:crypto=\"http://id.loc.gov/vocabulary/preservation/cryptographicHashFunctions/\"\n", | |
| " xmlns:bcodmo=\"http://lod.bco-dmo.org/id/\"\n", | |
| " xmlns:arpfo=\"http://vocab.ox.ac.uk/projectfunding#\"\n", | |
| " xmlns:tw=\"http://tw.rpi.edu/schema/\"\n", | |
| " xmlns:dcat=\"http://www.w3.org/ns/dcat#\"\n", | |
| " xmlns:time=\"http://www.w3.org/2006/time#\"\n", | |
| " xmlns:geo=\"http://www.w3.org/2003/01/geo/wgs84_pos#\"\n", | |
| " xmlns:geosparql=\"http://www.opengis.net/ont/geosparql#\"\n", | |
| " xmlns:sf=\"http://www.opengis.net/ont/sf#\"\n", | |
| " xmlns:void=\"http://rdfs.org/ns/void#\"\n", | |
| " xmlns:sd=\"http://www.w3.org/ns/sparql-service-description#\"\n", | |
| " xmlns:dctype=\"http://purl.org/dc/dcmitype/\"\n", | |
| " xmlns:prov=\"http://www.w3.org/ns/prov#\"\n", | |
| " xmlns:schema=\"http://schema.org/\"\n", | |
| " xmlns:geolink=\"http://schema.geolink.org/1.0/base/main#\">\n", | |
| "\n", | |
| "<head profile=\"http://www.w3.org/1999/xhtml/vocab\">\n", | |
| " <meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n", | |
| "<meta name=\"Generator\" content=\"Drupal 7 (http://drupal.org)\" />\n", | |
| "<link rel=\"canonical\" href=\"https://www.bco-dmo.org/dataset/3160\" />\n", | |
| "<link rel=\"shortlink\" href=\"/node/3160\" />\n", | |
| "<scr\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "# Now ask for the original again\n", | |
| "url = \"https://www.bco-dmo.org/dataset/3160\"\n", | |
| "headers = {\"Accept\":\"application/ld+json\"}\n", | |
| "response3 = requests.get(url, headers=headers, timeout=30)\n", | |
| "loghistory(response3)\n", | |
| "#print the first 2k chars\n", | |
| "print(response3.text[:2000])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": null, | |
| "id": "available-residence", | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [] | |
| } | |
| ], | |
| "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": "3.9.1" | |
| } | |
| }, | |
| "nbformat": 4, | |
| "nbformat_minor": 5 | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment