jules
/
DAAP_interface
2
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
Browse Source

description text extracted

master
jules 4 years ago
parent
328793e6c1
commit
0d67d6e2ad
1 changed files with 36 additions and 29 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 65
      daapinterface.py

65
daapinterface.py
View File

@ -70,16 +70,16 @@ def home():
@app.route("/browsethearchive") @app.route("/browsethearchive")
def browsethearchive(): def browsethearchive():
sparql.setQuery(''' sparql.setQuery('''
SELECT ?work ?workLabel ?image ?date WHERE { SELECT ?work ?workLabel ?image ?date WHERE {
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
?work wdt:P1 wd:Q1. ?work wdt:P1 wd:Q1.
OPTIONAL { ?work p:P30 ?statement. OPTIONAL { ?work p:P30 ?statement.
?statement ps:P30 ?image; ?statement ps:P30 ?image;
pq:P54 wd:Q90.} pq:P54 wd:Q90.}
OPTIONAL { ?work wdt:P13 ?date. } OPTIONAL { ?work wdt:P13 ?date. }
FILTER(?work != wd:Q57) FILTER(?work != wd:Q57)
} }
ORDER BY (?workLabel) ORDER BY (?workLabel)
''') ''')
sparql.setReturnFormat(JSON) sparql.setReturnFormat(JSON)
results = sparql.query().convert() results = sparql.query().convert()
@ -295,7 +295,7 @@ def artwork():
''') ''')
sparql.setReturnFormat(JSON) sparql.setReturnFormat(JSON)
artworkpublisher = sparql.query().convert() artworkpublisher = sparql.query().convert()
print(artworkpublisher) # print(artworkpublisher)
#####right middle #####right middle
@ -316,6 +316,7 @@ def artwork():
sparql.setReturnFormat(JSON) sparql.setReturnFormat(JSON)
artworkdescriptiondata = sparql.query().convert() artworkdescriptiondata = sparql.query().convert()
# print("hello") # print("hello")
# print(artwork_id)
# print(artworkdescriptiondata) # print(artworkdescriptiondata)
# print("bye") # print("bye")
@ -323,38 +324,44 @@ def artwork():
# print(type(dictionary)) # print(type(dictionary))
# get the description text or say there isn't any # get the description text or say there isn't any
# artworkdescriptiontext = None artworkdescriptiontext = None
# for x in dictionary['results']['bindings']: for x in dictionary['results']['bindings']:
# if "accessURLdescriptionPage" in x: if "accessURLdescriptionPage" in x:
# print("url for description present") print("url for description present")
print(x["accessURLdescriptionPage"]["value"])
accessURLdescriptionUrl = x["accessURLdescriptionPage"]["value"]
desc_url = re.search(r':Q(.*)', accessURLdescriptionUrl, re.DOTALL)
# print(desc_url.group(1))
desc_id=desc_url.group(1)
# # get the description content from wiki # # get the description content from wiki
# artworkdescriptioncontenturl = "https://daap.bannerrepeater.org/w/index.php?title=Description:"+artwork_id+"&action=render" 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 # # Make a GET request to fetch the raw HTML content
# html_content = requests.get(artworkdescriptioncontenturl).text html_content = requests.get(artworkdescriptioncontenturl).text
# # Parse the html content # # Parse the html content
# soup = BeautifulSoup(html_content, "lxml") soup = BeautifulSoup(html_content, "lxml")
# # print(soup.prettify()) # print the parsed data of html # # print(soup.prettify()) # print the parsed data of html
# # text=soup.find("div" , {"class" : "mw-parser-output"}) text=soup.find("div" , {"class" : "mw-parser-output"})
# text=soup.find_all("p") # text=soup.find_all("p")
# artworkdescriptiontext=Markup(text) artworkdescriptiontext=Markup(text)
# else: else:
# print("url for description absent") print("url for description absent")
# text="<p>Information not available</p>" text="<p>Information not available</p>"
# artworkdescriptiontext=Markup(text) artworkdescriptiontext=Markup(text)
artworkdescriptioncontenturl = "https://daap.bannerrepeater.org/w/index.php?title=Description:Q427&action=render" #description Q427 for testing purposes
# artworkdescriptioncontenturl = "https://daap.bannerrepeater.org/w/index.php?title=Description:Q427&action=render"
# Make a GET request to fetch the raw HTML content # Make a GET request to fetch the raw HTML content
html_content = requests.get(artworkdescriptioncontenturl).text # html_content = requests.get(artworkdescriptioncontenturl).text
# Parse the html content # Parse the html content
soup = BeautifulSoup(html_content, "lxml") # soup = BeautifulSoup(html_content, "lxml")
# print(soup.prettify()) # print the parsed data of html # print(soup.prettify()) # print the parsed data of html
text=soup.find("div" , {"class" : "mw-parser-output"}) # text=soup.find("div" , {"class" : "mw-parser-output"})
# text=soup.find_all("p") # text=soup.find_all("p")
artworkdescriptiontext=Markup(text) # artworkdescriptiontext=Markup(text)
print(artworkdescriptiontext) # print(artworkdescriptiontext)
############ right bottom LATER ############ right bottom LATER
# exhibitions + id to be changed # exhibitions + id to be changed

Write Preview
Loading…
Cancel
Save