DAAP_interface/daapinterface.py

# encoding=utf8

# # # # # # # # # # # # # # # # # # # # # # # # 
# REQUIREMENTS
# # # # # # # # # # # # # # # # # # # # # # # # 
from flask import send_file, Flask, Response, url_for, render_template, Markup, jsonify, redirect, request, flash, session, make_response
import requests
from SPARQLWrapper import SPARQLWrapper, JSON
import json
# import pandas as pd
# ##### IMPORTS FOR TEST WIKIPAGE
from lxml import html
from bs4 import BeautifulSoup
import re



# # # # # # # # # # # # # # # # # # # # # # # # 
# GETTING STARTED
# # # # # # # # # # # # # # # # # # # # # # # # 
app = Flask(__name__, static_url_path='', static_folder="static", template_folder="templates")
app.config['SEND_FILE_MAX_AGE_DEFAULT'] = 0
app.jinja_env.add_extension('jinja2.ext.loopcontrols')


# # # # # # # # # # # # # # # # # # # # # # # # 
# GETTING WIKIBASE DATA
# # # # # # # # # # # # # # # # # # # # # # # # 

sparql = SPARQLWrapper("https://query.daap.bannerrepeater.org/proxy/wdqs/bigdata/namespace/wdq/sparql")

# # # # # # # # # # # # # # # # # # # # # # # # 
# PAGES
# # # # # # # # # # # # # # # # # # # # # # # # 
@app.route("/")
def home():
    sparql.setQuery('''
    SELECT ?work ?workLabel ?image ?date ?dateadded WHERE {
    {
    SELECT ?work ?workLabel (SAMPLE(?date) AS ?date)
    WHERE
    { ?work wdt:P1 wd:Q1;
            wdt:P13 ?date.
      FILTER(?work != wd:Q57)
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?work ?workLabel
    ORDER BY ?workLabel
    }  
    {
    SELECT ?work ?workLabel (SAMPLE(?image) AS ?image)
    WHERE
    {   ?work wdt:P1 wd:Q1;
              p:P90 ?statement.
              ?statement ps:P90 ?image;
                         pq:P54 wd:Q90.
       FILTER(?work != wd:Q57)
       SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?work ?workLabel
    ORDER BY ?workLabel
    }      
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
    ?work wdt:P1 wd:Q1;
    wdt:P87 ?dateadded.
    FILTER(?work != wd:Q57)
    }
    ORDER BY DESC (?dateadded)
    LIMIT 12
    ''')
    sparql.setReturnFormat(JSON)
    results = sparql.query().convert()
    ImagesBanner = []
    # print(results)
    for publication in results["results"]["bindings"]:
        publication_title = publication["workLabel"]["value"]
        publication_uri = publication["work"]["value"]
        #if key exists
        if "date" in publication:
            publication_date = publication["date"]["value"]
        if "image" in publication:
            publication_image = publication["image"]["value"]
            ImagesBanner.append(publication_image) 
    ImagesBanner = ImagesBanner[-12:] 
    return render_template('home.html', results=results, ImagesBanner=ImagesBanner)


@app.route("/browsethearchive")
def browsethearchive():
    sparql.setQuery('''
    SELECT ?work ?workLabel ?image ?date WHERE {
    {
    SELECT ?work ?workLabel (SAMPLE(?date) AS ?date)
    WHERE
    { ?work wdt:P1 wd:Q1;
            wdt:P13 ?date.
      FILTER(?work != wd:Q57)
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?work ?workLabel
    ORDER BY ?workLabel
    }  
    ?work wdt:P1 wd:Q1.      
    OPTIONAL {?work p:P90 ?statement.
              ?statement ps:P90 ?image;
                         pq:P54 wd:Q90.}
    FILTER(?work != wd:Q57)
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }      
    }
    ORDER BY ?workLabel
    ''')
    sparql.setReturnFormat(JSON)
    results = sparql.query().convert()
    # print(results)
    for publication in results["results"]["bindings"]:
    	publication_title = publication["workLabel"]["value"]
    	publication_uri = publication["work"]["value"]
    	#if key exists
    	if "date" in publication:
    	    publication_date = publication["date"]["value"]
    	if "image" in publication:
    	    publication_image = publication["image"]["value"]
    return render_template('browsethearchive.html', results=results)

@app.route("/browsebycategory")
def browsebycategory():
    return render_template('browsebycategory.html')


##########################
# CATEGORIES TO BE BROWSED
#########################


######################### ARTIST INDEX
@app.route("/artistsindex")
def artistsindex():
    sparql.setQuery('''
        SELECT ?creators ?creatorsLabel ?creatorsAltLabel ?creatorsDescription 
        WHERE {
        {
        SELECT ?creators (COUNT(DISTINCT ?a) AS ?count) WHERE {
        ?a ?prop ?creators . 
        ?a wdt:P1 ?work .
        BIND (wdt:P9 AS ?prop) .
        BIND (wd:Q1 AS ?work) .
        } GROUP BY ?creators
        } . 
        SERVICE wikibase:label {
        bd:serviceParam wikibase:language "en" .
        }
        FILTER (?creators !=wd:Q82)
        }
        ORDER BY DESC(?count) ?creatorsLabel
        ''')
    sparql.setReturnFormat(JSON)
    results = sparql.query().convert()
    return render_template('artistsindex.html', results=results)

######################### PUBLISHERS INDEX
@app.route("/publishersindex")
def publishersindex():
    sparql.setQuery('''
        SELECT ?publishers ?publishersLabel ?publishersAltLabel ?publishersDescription WHERE {
  		{
    	SELECT ?publishers (COUNT(DISTINCT ?a) AS ?count) WHERE {
       	?a ?prop ?publishers . 
       	?a wdt:P1 ?work .
       	BIND (wdt:P10 AS ?prop) .
       	BIND (wd:Q1 AS ?work) .
    	} GROUP BY ?publishers
 		} . 
  		SERVICE wikibase:label {
    	bd:serviceParam wikibase:language "en" .
 	 	}
  		FILTER(?publishers != wd:Q83)
  		FILTER(?publishers != wd:Q71)
		}
        ORDER BY DESC(?count) ?publishersLabel
        ''')
    sparql.setReturnFormat(JSON)
    results = sparql.query().convert()
    return render_template('publishersindex.html', results=results)

######################### SELF PUBLISHED INDEX
@app.route("/selfpublishedindex")
def selfpublishedindex():
    sparql.setQuery('''
    SELECT ?work ?workLabel ?image ?date
    WHERE {
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
    ?work wdt:P1 wd:Q1;
    wdt:P10 wd:Q71.
    OPTIONAL {?work p:P90 ?statement.
              ?statement ps:P90 ?image;
                         pq:P54 wd:Q90.}
    OPTIONAL { ?work wdt:P13 ?date. } 
    FILTER(?work != wd:Q57)
    }
        ''')
    sparql.setReturnFormat(JSON)
    results = sparql.query().convert()
    return render_template('selfpublishedindex.html', results=results)

######################### ZINES INDEX
@app.route("/zinesindex")
def zinesindex():
    sparql.setQuery('''
    SELECT ?work ?workLabel ?image ?date
    WHERE {
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
    ?work wdt:P1 wd:Q1;
    wdt:P16 wd:Q152.
    OPTIONAL {?work p:P90 ?statement.
              ?statement ps:P90 ?image;
                         pq:P54 wd:Q90.}
    OPTIONAL { ?work wdt:P13 ?date. } 
    FILTER(?work != wd:Q57)
    }
    ORDER BY ?workLabel
        ''')
    sparql.setReturnFormat(JSON)
    results = sparql.query().convert()
    # print(results)
    return render_template('zinesindex.html', results=results)


##########################
# DETAILED INDIVIDUAL PAGES
#########################

######################### ARTWORK
@app.route("/artwork", methods=['GET'])
def artwork():
    artwork_id = request.args.get('id')

# Artwork Intro / Top of the page
    sparql.setQuery('''
    SELECT ?work ?workLabel ?workDescription ?itemtypeLabel
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    ?work wdt:P1 ?itemtype.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    artworkintro = sparql.query().convert()

# Image(s)
# query for later
    sparql.setQuery('''
    SELECT ?image ?depictsLabel ?licenseLabel
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    ?work wdt:P90 ?image.
    OPTIONAL { ?work p:P90 ?statement2.
    ?statement2 ps:P90 ?image;
    pq:P54 ?depicts;
    pq:P56 ?license.}
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".} 
    }
    ''')

    sparql.setReturnFormat(JSON)
    artworkimages = sparql.query().convert()
    # print(artworkimages)

# Links and downloads
    sparql.setQuery('''
    SELECT ?DownloadDigitalFacsimile ?DigitalFacsimileExternalLink ?DigitalFacsimileExternalLink2
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    OPTIONAL {?work wdt:P32 ?DownloadDigitalFacsimile.}
    OPTIONAL {?work wdt:P34 ?DigitalFacsimileExternalLink.}
    OPTIONAL {?work wdt:P33 ?DigitalFacsimileExternalLink2.}
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".} 
    }''')
    sparql.setReturnFormat(JSON)
    artworklinksanddownloads = sparql.query().convert()

#  Other digital artefacts
    sparql.setQuery('''
    SELECT ?ImageFile ?AudioFile ?VideoFile
    WHERE
    {
        {
        SELECT ?ImageFile WHERE {
        VALUES ?work {wd:'''+artwork_id+'''}
        OPTIONAL {?work p:P35 ?statement.
            ?statement ps:P35 ?ImageFile;
                       pq:P16 wd:Q85.}
        }}
        {
        SELECT ?AudioFile WHERE {
        VALUES ?work {wd:'''+artwork_id+'''}
        OPTIONAL {?work p:P35 ?statement.
            ?statement ps:P35 ?AudioFile;
                       pq:P16 wd:Q28.} 
        }}
        {
        SELECT ?VideoFile WHERE {
        VALUES ?work {wd:'''+artwork_id+'''}
        OPTIONAL {?work p:P35 ?statement.
            ?statement ps:P35 ?VideoFile;
                       pq:P16 wd:Q27.} 
        }}
        SERVICE wikibase:label { bd:serviceParam wikibase:language "en".} 
    } 
    ''')
    sparql.setReturnFormat(JSON)
    artworkartefacts = sparql.query().convert()
    # print(artworkartefacts)


# Distributor Links
    sparql.setQuery('''
    SELECT ?distributorLinks
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''} 
    OPTIONAL {?work wdt:P37 ?distributorLinks.} 
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".} 
    } 
    ''')
    sparql.setReturnFormat(JSON)
    artworkdistributorlinks = sparql.query().convert()


######### Right top
# contributors
    sparql.setQuery('''
    SELECT DISTINCT ?creators ?creatorsLabel (group_concat(?creatorRolesLabel; separator="; ") as ?role)
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    ?work wdt:P9 ?creators.
    OPTIONAL { ?work p:P9 ?statement1.
    ?statement1 ps:P9 ?creators;
    pq:P49 ?creatorRoles. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".
    ?creators rdfs:label ?creatorsLabel.
    ?creatorRoles rdfs:label ?creatorRolesLabel. } 
    }
    GROUP BY ?creators ?creatorsLabel
    ORDER BY ?creatorsLabel
    ''')
    sparql.setReturnFormat(JSON)
    artworkcontributors = sparql.query().convert()

# date
    sparql.setQuery('''
    SELECT ?date ?sourceLabel
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    ?work wdt:P13 ?date.
    OPTIONAL { ?work p:P13 ?statement1.
    ?statement1 ps:P13 ?date;
    pq:P50 ?source. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".} 
    }
    ''')
    sparql.setReturnFormat(JSON)
    artworkdate = sparql.query().convert()

# publishers
    sparql.setQuery('''
    SELECT DISTINCT ?publishers ?publishersLabel (group_concat(?publishersRolesLabel; separator="; ") as ?role)
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    ?work wdt:P10 ?publishers.
    OPTIONAL { ?work p:P10 ?statement1.
    ?statement1 ps:P10 ?publishers;
    pq:P49 ?creatorRoles. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".
    ?publishers rdfs:label ?publishersLabel.
    ?publishersRoles rdfs:label ?publishersRolesLabel. } 
    }
    GROUP BY ?publishers ?publishersLabel
    ORDER BY ?publishersLabel
    ''')
    sparql.setReturnFormat(JSON)
    artworkpublisher = sparql.query().convert()

#####right middle
# description + id to be changed
    sparql.setQuery('''
    SELECT ?accessURLdescriptionPage ?authordescriptionPage ?authordescriptionPageLabel ?datedescriptionPage ?sourcedescriptionPage ?sourcedescriptionPageLabel
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    ?work wdt:P65 ?descriptionPage.
    OPTIONAL { ?descriptionPage wdt:P4 ?accessURLdescriptionPage. }
    OPTIONAL { ?descriptionPage wdt:P9 ?authordescriptionPage. }  
    OPTIONAL { ?descriptionPage wdt:P13 ?datedescriptionPage. } 
    OPTIONAL { ?descriptionPage wdt:P50 ?sourcedescriptionPage. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    artworkdescriptiondata = sparql.query().convert()


    for x in artworkdescriptiondata['results']['bindings']:
        if "accessURLdescriptionPage" in x:
            accessURLdescriptionUrl = x["accessURLdescriptionPage"]["value"]
            desc_url = re.search(r':Q(.*)', accessURLdescriptionUrl, re.DOTALL)
            desc_id=desc_url.group(1)
    #         # get the description content from wiki 
            artworkdescriptioncontenturl = "https://daap.bannerrepeater.org/w/index.php?title=Description:Q"+desc_id+"&action=render"
    #         # Make a GET request to fetch the raw HTML content
            html_content = requests.get(artworkdescriptioncontenturl).text
    #         # Parse the html content
            soup = BeautifulSoup(html_content, "lxml")
    #         # print(soup.prettify()) # print the parsed data of html
            text=soup.find("div" , {"class" : "mw-parser-output"})
    #         text=soup.find_all("p")
            # text=Markup(text)
            # artworkdescriptiontext.append(text)
            x["text"] = text
        else:
            # print("url for description absent")
            text="<p>Information not available</p>"
            x["text"] = text

    # print(artworkdescriptiondata)

# exhibitions + id to be changed
    sparql.setQuery('''
    SELECT ?accessURLexhibitionHisPage ?authorexhibitionHisPageLabel ?dateexhibitionHisPage ?sourceexhibitionHisPage    
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''} 
    ?work wdt:P66 ?exhibitionHisPage.
    OPTIONAL { ?exhibitionHisPage wdt:P4 ?accessURLexhibitionHisPage. }
    OPTIONAL { ?exhibitionHisPage wdt:P9 ?authorexhibitionHisPage. }
    OPTIONAL { ?exhibitionHisPage wdt:P13 ?dateexhibitionHisPage. }
    OPTIONAL { ?exhibitionHisPage wdt:P50 ?sourceexhibitionHisPage. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    artworkexhibitiondata = sparql.query().convert()

    # get the text from the url
    for x in artworkexhibitiondata['results']['bindings']:
        if "accessURLexhibitionHisPage" in x:
            accessURLexhibitionHisPage = x["accessURLexhibitionHisPage"]["value"]
            desc_url = re.search(r':Q(.*)', accessURLexhibitionHisPage, re.DOTALL)
            # print(desc_url.group(1))
            desc_id=desc_url.group(1)
    #         # get the description content from wiki 
            artworkexhibitioncontenturl = "https://daap.bannerrepeater.org/w/index.php?title=History:Q"+desc_id+"&action=render"
    #         # Make a GET request to fetch the raw HTML content
            html_content = requests.get(artworkexhibitioncontenturl).text
    #         # Parse the html content
            soup = BeautifulSoup(html_content, "lxml")
    #         # print(soup.prettify()) # print the parsed data of html
            text=soup.find("div" , {"class" : "mw-parser-output"})
    #         text=soup.find_all("p")
            # artworkexhibitiontext=Markup(text)
            x['text']=text
        else:
            # print("url for description absent")
            text="<p>Information not available</p>"
            # artworkexhibitiontext=Markup(text)
            x['text']=text



############## bottom
# copies in collection
    sparql.setQuery('''
    SELECT ?copiesCollections ?copiesCollectionsLabel ?collection ?collectionLabel ?image
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    ?work wdt:P43 ?copiesCollections.
    ?copiesCollections wdt:P47 ?collection.
    OPTIONAL { ?collection wdt:P90 ?image. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }  ''')
    sparql.setReturnFormat(JSON)
    copiesincollection = sparql.query().convert()

# related works

    sparql.setQuery('''
    SELECT ?relatedWorks ?relatedWorksLabel ?image ?daterelatedWorks 
    WHERE {
    {
    SELECT ?relatedWorks ?relatedWorksLabel (SAMPLE(?daterelatedWorks) AS ?daterelatedWorks)
    WHERE
    { VALUES ?work {wd:'''+artwork_id+'''}
      ?work wdt:P44 ?relatedWorks.
      OPTIONAL {?relatedWorks wdt:P13 ?daterelatedWorks.}
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?relatedWorks ?relatedWorksLabel
    ORDER BY ?relatedWorksLabel
    }  
    {
    SELECT ?relatedWorks ?relatedWorksLabel (SAMPLE(?image) AS ?image)
    WHERE
    { VALUES ?work {wd:'''+artwork_id+'''}
      ?work wdt:P44 ?relatedWorks.
      OPTIONAL {?relatedWorks wdt:P90 ?image.}
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?relatedWorks ?relatedWorksLabel
    ORDER BY ?relatedWorksLabel
    }   
    }
    ''')
    sparql.setReturnFormat(JSON)
    relatedworks = sparql.query().convert()

#  lists
    sparql.setQuery('''
    SELECT ?list ?listLabel ?image ?date
    WHERE
    {
    VALUES ?work {wd:'''+artwork_id+'''}
    ?work wdt:P45 ?list.
    OPTIONAL {?list wdt:P13 ?date.}
    OPTIONAL {?list wdt:P90 ?image.}
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".} 
    } 
    ''')
    sparql.setReturnFormat(JSON)
    artworklists = sparql.query().convert()

    return render_template('artwork.html', artwork_id=artwork_id, artworkintro=artworkintro, artworkimages=artworkimages, artworklinksanddownloads=artworklinksanddownloads, artworkartefacts=artworkartefacts, artworkdistributorlinks=artworkdistributorlinks, artworkcontributors=artworkcontributors, artworkdate=artworkdate, artworkpublisher=artworkpublisher, artworkdescriptiondata=artworkdescriptiondata, artworkexhibitiondata=artworkexhibitiondata,  artworklists=artworklists, copiesincollection=copiesincollection, relatedworks=relatedworks)


######################### COPY ITEM
@app.route("/copy", methods=['GET'])
def copy():
    copy_id = request.args.get('id')

    # Intro
    sparql.setQuery('''
    SELECT ?item ?itemLabel ?itemDescription ?itemtypeLabel
    {
    VALUES ?item {wd:'''+copy_id+'''}
    ?item wdt:P1 ?itemtype.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    copyintro = sparql.query().convert()

# image
    sparql.setQuery('''
    SELECT ?image ?depictsLabel ?licenseLabel
    WHERE
    {
    VALUES ?item {wd:'''+copy_id+'''}
    ?item wdt:P90 ?image.
    OPTIONAL { ?work p:P90 ?statement2.
    ?statement2 ps:P90 ?image;
      pq:P54 ?depicts;
      pq:P56 ?license.}
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".} 
    }
    ''')
    sparql.setReturnFormat(JSON)
    copyimage = sparql.query().convert()

# copy of
    sparql.setQuery('''
    SELECT ?work ?workLabel
    WHERE
    {
    VALUES ?item {wd:'''+copy_id+'''}
    ?item wdt:P46 ?work.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }  
    }
    ''')
    sparql.setReturnFormat(JSON)
    copyof = sparql.query().convert()

# collection
    sparql.setQuery('''
    SELECT ?collection ?collectionLabel
    WHERE
    {
    VALUES ?item {wd:'''+copy_id+'''}
    ?item wdt:P47 ?collection.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    copycollection = sparql.query().convert()

# inventory number
    sparql.setQuery('''
    SELECT ?inventoryNumber
    WHERE
    {
    VALUES ?item {wd:'''+copy_id+'''}    
    ?item wdt:P48 ?inventoryNumber.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    copyinventorynumber = sparql.query().convert()


#  copy description
    sparql.setQuery('''
    SELECT ?accessURLdescriptionPage ?authordescriptionPageLabel ?datedescriptionPage ?sourcedescriptionPageLabel
    WHERE
    {
    VALUES ?item {wd:'''+copy_id+'''}
    ?item wdt:P65 ?descriptionPage.
    OPTIONAL { ?descriptionPage wdt:P4 ?accessURLdescriptionPage. }
    OPTIONAL { ?descriptionPage wdt:P9 ?authordescriptionPage. }  
    OPTIONAL { ?descriptionPage wdt:P13 ?datedescriptionPage. } 
    OPTIONAL { ?descriptionPage wdt:P50 ?sourcedescriptionPage. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    copydescription = sparql.query().convert()

    for x in copydescription['results']['bindings']:
        if "accessURLdescriptionPage" in x:
            accessURLdescURL = x["accessURLdescriptionPage"]["value"]
            desc_url = re.search(r':Q(.*)', accessURLdescURL, re.DOTALL)
            desc_id=desc_url.group(1)
    #         # get the description content from wiki 
            copydesccontenturl = "https://daap.bannerrepeater.org/w/index.php?title=Description:Q"+desc_id+"&action=render"
    #         # Make a GET request to fetch the raw HTML content
            html_content = requests.get(copydesccontenturl).text
    #         # Parse the html content
            soup = BeautifulSoup(html_content, "lxml")
    #         # print(soup.prettify()) # print the parsed data of html
            text=soup.find("div" , {"class" : "mw-parser-output"})
    #         text=soup.find_all("p")
            # text=Markup(text)
            # artworkdescriptiontext.append(text)
            x["text"] = text
        else:
            # print("url for description absent")
            text="<p>Information not available</p>"
            x["text"] = text


    return render_template('copy.html', copy_id=copy_id, copyintro=copyintro, copyimage=copyimage, copyof=copyof, copycollection=copycollection, copyinventorynumber=copyinventorynumber, copydescription=copydescription)


######################### ITEM : COLLECTIVE - PERSON - ORGANISATION

@app.route("/item", methods=['GET'])
def item():
    item_id = request.args.get('id')

# Intro
    sparql.setQuery('''
    SELECT ?item ?itemLabel ?itemDescription ?itemtypeLabel
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P1 ?itemtype.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
	''')
    sparql.setReturnFormat(JSON)
    itemintro = sparql.query().convert()


# image
    sparql.setQuery('''
    SELECT ?image ?depictsLabel ?licenseLabel
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P90 ?image.
    OPTIONAL { ?work p:P90 ?statement2.
    ?statement2 ps:P90 ?image;
      pq:P54 ?depicts;
      pq:P56 ?license.}
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en".} 
    }
    ''')
    sparql.setReturnFormat(JSON)
    itemimage = sparql.query().convert()


# official website
    sparql.setQuery('''
    SELECT ?website
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P61 ?website.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    itemwebsite = sparql.query().convert()

# wikidata id
    sparql.setQuery('''
    SELECT ?WikidataID
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P3 ?WikidataID.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    itemwikidataID = sparql.query().convert()

# viaf ID
    sparql.setQuery('''
    SELECT ?VIAFID
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P80 ?VIAFID.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    itemviafID = sparql.query().convert()


# PERSON gender
 # for test:Q82}
    sparql.setQuery('''
    SELECT ?genderLabel
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P86 ?gender.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    persongender = sparql.query().convert()


# PERSON pronouns
    sparql.setQuery('''
    SELECT ?pronounLabel
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P85 ?pronoun.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }  
    }
    ''')
    sparql.setReturnFormat(JSON)
    personpronouns = sparql.query().convert()


#  ORGANISATION location
    sparql.setQuery('''
    SELECT ?locationLabel
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P83 ?location.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    orglocation = sparql.query().convert()

#  ORGANISATION country
    sparql.setQuery('''
    SELECT ?countryLabel
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P84 ?country.
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    orgcountry = sparql.query().convert()

# COLLECTIVE MEMBERS
 # for test:Q309}
    sparql.setQuery('''
    SELECT ?members ?membersLabel
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P74 ?members. 
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    collectivemembers = sparql.query().convert()

# PERSON biography
    sparql.setQuery('''
    SELECT ?accessURLbioPage ?authorBioPageLabel ?dateBioPage ?sourceBioPageLabel
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P67 ?bioPage.
    OPTIONAL { ?bioPage wdt:P4 ?accessURLbioPage. }
    OPTIONAL { ?bioPage wdt:P9 ?authorBioPage. }
    OPTIONAL { ?bioPage wdt:P13 ?dateBioPage. }
    OPTIONAL { ?bioPage wdt:P50 ?sourceBioPage. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    personbiography = sparql.query().convert()

    for x in personbiography['results']['bindings']:
        if "accessURLbioPage" in x:
            accessURLbioURL = x["accessURLbioPage"]["value"]
            desc_url = re.search(r':Q(.*)', accessURLbioURL, re.DOTALL)
            desc_id=desc_url.group(1)
    #         # get the description content from wiki 
            personbiocontenturl = "https://daap.bannerrepeater.org/w/index.php?title=Biography:Q"+desc_id+"&action=render"
    #         # Make a GET request to fetch the raw HTML content
            html_content = requests.get(personbiocontenturl).text
    #         # Parse the html content
            soup = BeautifulSoup(html_content, "lxml")
    #         # print(soup.prettify()) # print the parsed data of html
            text=soup.find("div" , {"class" : "mw-parser-output"})
    #         text=soup.find_all("p")
            # text=Markup(text)
            # artworkdescriptiontext.append(text)
            x["text"] = text
        else:
            # print("url for description absent")
            text="<p>Information not available</p>"
            x["text"] = text


#  COLLECTIVE AND INSTITUTION DESCRIPTION
    sparql.setQuery('''
    SELECT ?accessURLdescriptionPage ?authordescriptionPageLabel ?datedescriptionPage ?sourcedescriptionPageLabel
    WHERE
    {
    VALUES ?item {wd:'''+item_id+'''}
    ?item wdt:P65 ?descriptionPage.
    OPTIONAL { ?descriptionPage wdt:P4 ?accessURLdescriptionPage. }
    OPTIONAL { ?descriptionPage wdt:P9 ?authordescriptionPage. }  
    OPTIONAL { ?descriptionPage wdt:P13 ?datedescriptionPage. } 
    OPTIONAL { ?descriptionPage wdt:P50 ?sourcedescriptionPage. }
    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    ''')
    sparql.setReturnFormat(JSON)
    colorgdescription = sparql.query().convert()

    for x in colorgdescription['results']['bindings']:
        if "accessURLdescriptionPage" in x:
            accessURLdescURL = x["accessURLdescriptionPage"]["value"]
            desc_url = re.search(r':Q(.*)', accessURLdescURL, re.DOTALL)
            desc_id=desc_url.group(1)
    #         # get the description content from wiki 
            itemdesccontenturl = "https://daap.bannerrepeater.org/w/index.php?title=Description:Q"+desc_id+"&action=render"
    #         # Make a GET request to fetch the raw HTML content
            html_content = requests.get(itemdesccontenturl).text
    #         # Parse the html content
            soup = BeautifulSoup(html_content, "lxml")
    #         # print(soup.prettify()) # print the parsed data of html
            text=soup.find("div" , {"class" : "mw-parser-output"})
    #         text=soup.find_all("p")
            # text=Markup(text)
            # artworkdescriptiontext.append(text)
            x["text"] = text
        else:
            # print("url for description absent")
            text="<p>Information not available</p>"
            x["text"] = text


# creator of
    sparql.setQuery('''
    SELECT ?Works ?WorksLabel ?image ?dateWorks 
    WHERE {
    {
    SELECT ?Works ?WorksLabel (SAMPLE(?dateWorks) AS ?dateWorks)
    WHERE
    {
      VALUES ?item {wd:'''+item_id+'''}
      ?Works wdt:P1 wd:Q1;
             wdt:P9 ?item;
             wdt:P13 ?dateWorks.
 
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?Works ?WorksLabel
    ORDER BY ?WorksLabel
    }
    {
    SELECT ?Works ?WorksLabel (SAMPLE(?image) AS ?image)
    WHERE
    {
      VALUES ?item {wd:'''+item_id+'''}
      ?Works wdt:P1 wd:Q1;
             wdt:P9 ?item.
      OPTIONAL {?Works wdt:P90 ?image.}
            SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?Works ?WorksLabel
    ORDER BY ?WorksLabel
    }
    }
        ''')
    sparql.setReturnFormat(JSON)
    item_creatorof = sparql.query().convert()


# publisher of
    sparql.setQuery('''
    SELECT ?Works ?WorksLabel ?image ?dateWorks 
    WHERE {
    {
    SELECT ?Works ?WorksLabel (SAMPLE(?dateWorks) AS ?dateWorks)
    WHERE
    {
      VALUES ?item {wd:'''+item_id+'''}
      ?Works wdt:P1 wd:Q1;
             wdt:P10 ?item;
             wdt:P13 ?dateWorks.
 
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?Works ?WorksLabel
    ORDER BY ?WorksLabel
    }
    {
    SELECT ?Works ?WorksLabel (SAMPLE(?image) AS ?image)
    WHERE
    {
      VALUES ?item {wd:'''+item_id+'''}
      ?Works wdt:P1 wd:Q1;
             wdt:P10 ?item.
      OPTIONAL {?Works wdt:P90 ?image.}
            SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?Works ?WorksLabel
    ORDER BY ?WorksLabel
    }
    }
    ''')
    sparql.setReturnFormat(JSON)
    item_publisherof = sparql.query().convert()

# commissioned
    sparql.setQuery('''
    SELECT ?Works ?WorksLabel ?image ?dateWorks 
    WHERE {
    {
    SELECT ?Works ?WorksLabel (SAMPLE(?dateWorks) AS ?dateWorks)
    WHERE
    {
      VALUES ?item {wd:'''+item_id+'''}
      ?Works wdt:P1 wd:Q1;
             wdt:P14 ?item;
             wdt:P13 ?dateWorks.
 
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?Works ?WorksLabel
    ORDER BY ?WorksLabel
    }
    {
    SELECT ?Works ?WorksLabel (SAMPLE(?image) AS ?image)
    WHERE
    {
      VALUES ?item {wd:'''+item_id+'''}
      ?Works wdt:P1 wd:Q1;
             wdt:P14 ?item.
      OPTIONAL {?Works wdt:P90 ?image.}
            SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    }
    GROUP BY ?Works ?WorksLabel
    ORDER BY ?WorksLabel
    }
    }
    ''')
    sparql.setReturnFormat(JSON)
    item_commissioned = sparql.query().convert()


 
    return render_template("item.html", item_id=item_id, item_creatorof=item_creatorof, itemwebsite=itemwebsite, itemwikidataID=itemwikidataID, itemviafID=itemviafID, item_publisherof=item_publisherof, item_commissioned=item_commissioned, itemintro=itemintro, itemimage=itemimage, personbiography=personbiography, persongender=persongender, personpronouns=personpronouns, collectivemembers=collectivemembers, orglocation=orglocation, orgcountry=orgcountry, colorgdescription=colorgdescription)


######################### ORGANISATION
# @app.route("/organisation", methods=['GET'])
# def organisation():
#     org_id = request.args.get('id')
#     return render_template("organisation.html")


#########################
# PAGES FROM WIKI
#########################


######################### ABOUT
@app.route("/about")
def about():
    url="https://daap.bannerrepeater.org/w/index.php?title=About&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    # A problem with image src obtention was solved by using absolute paths rather than traditional wiki syntax

    # replaceString = "wiki/Special:Redirect/file/"
    # cleanSoup = BeautifulSoup(str(text).replace("wiki/File:", replaceString))

    # for a in soup.find_all('a', href=True): 
    #     if a.text: 
    #         print(a['href'])


    # replace src from img zith href from a href and remove the a 

    text=Markup(text)
    return render_template('about.html', text=text)


######################### UPLOAD
@app.route("/upload")
def upload():
    url="https://daap.bannerrepeater.org/w/index.php?title=Upload&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    text=Markup(text)

    return render_template('upload.html', text=text)

# #################### TEAM
@app.route("/team")
def team():
    url="https://daap.bannerrepeater.org/w/index.php?title=Team&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")

    text=Markup(text)
    return render_template('team.html', text=text)

# #################### CASE STUDY
@app.route("/casestudy")
def casestudy():
    url="https://daap.bannerrepeater.org/w/index.php?title=Carolee_Schneemann_case_study&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")

    text=Markup(text)
    return render_template('casestudy.html', text=text)



# #################### CODE OF CONDUCT
@app.route("/codeofconduct")
def codeofconduct():
    url="https://daap.bannerrepeater.org/w/index.php?title=Code_of_Conduct&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")

    text=Markup(text)
    return render_template('codeofconduct.html', text=text)


# #################### SEARCH TOOLS
@app.route("/searchtools")
def searchtools():
    url="https://daap.bannerrepeater.org/w/index.php?title=Search_Tools&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")

    text=Markup(text)
    return render_template('searchtools.html', text=text)

######################### TUTORIAL
@app.route("/tutorials")
def tutorials():
    url="https://daap.bannerrepeater.org/w/index.php?title=Tutorials&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    text=Markup(text)
    return render_template('tutorials.html',  text=text)



######################### TUTORIAL 1
@app.route("/tutorial_1")
def tutorial_1():
    url="https://daap.bannerrepeater.org/w/index.php?title=Tutorial_1&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    text=Markup(text)
    return render_template('tutorials.html',  text=text)

######################### TUTORIAL 2 
@app.route("/tutorial_2")
def tutorial_2():
    url="https://daap.bannerrepeater.org/w/index.php?title=Tutorial_2&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    text=Markup(text)
    return render_template('tutorials.html',  text=text)

######################### TUTORIAL 3 
@app.route("/tutorial_3")
def tutorial_3():
    url="https://daap.bannerrepeater.org/w/index.php?title=Tutorial_3&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    text=Markup(text)
    return render_template('tutorials.html',  text=text)

######################### TUTORIAL 4 
@app.route("/tutorial_4")
def tutorial_4():
    url="https://daap.bannerrepeater.org/w/index.php?title=Tutorial_4&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    text=Markup(text)
    return render_template('tutorials.html',  text=text)


######################### TUTORIAL 5 
@app.route("/tutorial_5")
def tutorial_5():
    url="https://daap.bannerrepeater.org/w/index.php?title=Tutorial_5&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    text=Markup(text)
    return render_template('tutorials.html',  text=text)


######################### TUTORIAL 6 
@app.route("/tutorial_6")
def tutorial_6():
    url="https://daap.bannerrepeater.org/w/index.php?title=Tutorial_6&action=render"
    # Make a GET request to fetch the raw HTML content
    html_content = requests.get(url).text
    # Parse the html content
    soup = BeautifulSoup(html_content, "lxml")
    # print(soup.prettify()) # print the parsed data of html

    text=soup.find("html")
    text=Markup(text)
    return render_template('tutorials.html',  text=text)







######################### LOGIN
#Goes to wikibase page



#  ALL NAME
#  https://daap.bannerrepeater.org/w/api.php?action=query&meta=siteinfo&siprop=namespaces|namespacealiases

# replace or insert tags
# https://stackoverflow.com/questions/2073541/search-and-replace-in-html-with-beautifulsoup