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.jinja_env.add_extension('jinja2.ext.loopcontrols')


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

sparql = SPARQLWrapper("https://query.daap.bannerrepeater.org/proxy/wdqs/bigdata/namespace/wdq/sparql")
sparql2 = SPARQLWrapper("https://query.daap.bannerrepeater.org/proxy/wdqs/bigdata/namespace/wdq/sparql")
sparql3 = SPARQLWrapper("https://query.daap.bannerrepeater.org/proxy/wdqs/bigdata/namespace/wdq/sparql")


# # # # # # # # # # # # # # # # # # # # # # # # 
# PAGES
# # # # # # # # # # # # # # # # # # # # # # # # 
@app.route("/")
def home():
    sparql.setQuery('''
        SELECT ?work ?workLabel ?image ?date WHERE {
  SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
  ?work wdt:P1 wd:Q1.
  OPTIONAL { ?work p:P30 ?statement.
              ?statement ps:P30 ?image;
                         pq:P54 wd:Q90.}
  OPTIONAL { ?work wdt:P13 ?date. }
  FILTER(?work != wd:Q57)
}
ORDER BY (?workLabel)
    ''')
    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 {
  SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
  ?work wdt:P1 wd:Q1.
  OPTIONAL { ?work p:P30 ?statement.
              ?statement ps:P30 ?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)
    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()
    print(results)
    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 ?workAltLabel ?workDescription 
        WHERE {
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
        ?work wdt:P1 wd:Q1;
        wdt:P10 wd:Q71.
        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 ?workAltLabel ?workDescription 
        WHERE {
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
        ?work wdt:P1 wd:Q1;
        wdt:P16 wd:Q152.
        FILTER(?work != wd:Q57)
        }
        ''')
    sparql.setReturnFormat(JSON)
    results = sparql.query().convert()
    return render_template('zinesindex.html', results=results)


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

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

    sparql.setQuery('''
    SELECT ?work ?workLabel ?workDescription ?propLabel ?b ?bLabel ?creators ?creatorsLabel ?creatorRoles ?creatorRolesLabel ?image ?depicts ?depictsLabel ?license ?licenseLabel
    WHERE
    {
  VALUES ?work {wd:'''+artwork_id+'''}
  ?work ?a ?b.
  
  OPTIONAL { ?work wdt:P9 ?creators. }
  OPTIONAL { ?work p:P9 ?statement1.
    ?statement1 ps:P9 ?creators;
      pq:P49 ?creatorRoles. }
  OPTIONAL { ?work wdt:P30 ?image. }
  OPTIONAL { ?work p:P30 ?statement2.
    ?statement2 ps:P30 ?image;
      pq:P54 ?depicts;
      pq:P56 ?license.}
  
  SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
  ?prop wikibase:directClaim ?a .
}    ''')
    sparql.setReturnFormat(JSON)
    artwork = sparql.query().convert()
    print(artwork)

    artwork_url = "https://daap.bannerrepeater.org/wiki/Item:Q92"
    artwork_title = "the human printer"
    artwork_description = "short description"
    return render_template('artwork.html', artwork_title=artwork_title, artwork_description=artwork_description, artwork=artwork, artwork_id=artwork_id)

######################### PERSON
@app.route("/person", methods=['GET'])
def person():
    person_id = request.args.get('id')
    sparql.setQuery('''

    SELECT ?item ?itemLabel ?itemDescription ?propLabel ?b ?bLabel
    WHERE
    {
    VALUES ?item {wd:'''+person_id+'''}
    ?item ?a ?b.

    SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } 
    ?prop wikibase:directClaim ?a .
    }
	''')
    sparql.setReturnFormat(JSON)
    person_details = sparql.query().convert()
    print(person_details)


    sparql2.setQuery('''
        SELECT ?work ?workLabel ?image ?date 
        WHERE {
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
        ?work wdt:P1 wd:Q1.
        ?work wdt:P9 wd:'''+person_id+'''.
        OPTIONAL { ?work wdt:P30 ?image. }
        OPTIONAL { ?work wdt:P13 ?date. }
        FILTER(?work != wd:Q57)
        }
        ORDER BY (?workLabel)
        ''')
    sparql2.setReturnFormat(JSON)
    person_creatorof = sparql2.query().convert()
    
    sparql3.setQuery('''
        SELECT ?work ?workLabel ?image ?date 
        WHERE {
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
        ?work wdt:P1 wd:Q1.
        ?work wdt:P10 wd:'''+person_id+'''.
        OPTIONAL { ?work wdt:P30 ?image. }
        OPTIONAL { ?work wdt:P13 ?date. }
        FILTER(?work != wd:Q57)
        }
        ORDER BY (?workLabel)
    	''')
    sparql3.setReturnFormat(JSON)
    person_publisherof = sparql2.query().convert()

    person_url = ""
    person_name = "the name"
    person_description = "short bio"
    return render_template("person.html", person_id=person_id, person_creatorof=person_creatorof, person_publisherof=person_publisherof, person_details=person_details)



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

######################### SEARCH TOOLS
@app.route("/searchtools")
def searchtools():
    return render_template('searchtools.html')

######################### 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")
    # adapt the path to img with regex

    # 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)

######################### TUTORIAL
@app.route("/tutorials")
def tutorials():
    return render_template('tutorials.html')


######################### 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)


# #################### 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)




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

# ###################
# TEST 

response = requests.get(
    'https://daap.bannerrepeater.org/w/api.php',
    params={
        'action': 'parse',
        'page': 'Test',
        'format': 'json',
    }).json()
raw_html = response['parse']['text']['*']
document = html.document_fromstring(raw_html)
first_p = document.xpath('//p')[0]
intro_text = first_p.text_content()
print(intro_text)


#  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