Browse Source

description text extracted

master
jules 4 years ago
parent
commit
0d67d6e2ad
  1. 53
      daapinterface.py

53
daapinterface.py

@ -78,8 +78,8 @@ def browsethearchive():
pq:P54 wd:Q90.}
OPTIONAL { ?work wdt:P13 ?date. }
FILTER(?work != wd:Q57)
}
ORDER BY (?workLabel)
}
ORDER BY (?workLabel)
''')
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
@ -295,7 +295,7 @@ def artwork():
''')
sparql.setReturnFormat(JSON)
artworkpublisher = sparql.query().convert()
print(artworkpublisher)
# print(artworkpublisher)
#####right middle
@ -316,6 +316,7 @@ def artwork():
sparql.setReturnFormat(JSON)
artworkdescriptiondata = sparql.query().convert()
# print("hello")
# print(artwork_id)
# print(artworkdescriptiondata)
# print("bye")
@ -323,38 +324,44 @@ def artwork():
# print(type(dictionary))
# get the description text or say there isn't any
# artworkdescriptiontext = None
# for x in dictionary['results']['bindings']:
# if "accessURLdescriptionPage" in x:
# print("url for description present")
artworkdescriptiontext = None
for x in dictionary['results']['bindings']:
if "accessURLdescriptionPage" in x:
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
# 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
# html_content = requests.get(artworkdescriptioncontenturl).text
html_content = requests.get(artworkdescriptioncontenturl).text
# # Parse the html content
# soup = BeautifulSoup(html_content, "lxml")
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("div" , {"class" : "mw-parser-output"})
# text=soup.find_all("p")
# artworkdescriptiontext=Markup(text)
# else:
# print("url for description absent")
# text="<p>Information not available</p>"
# artworkdescriptiontext=Markup(text)
artworkdescriptiontext=Markup(text)
else:
print("url for description absent")
text="<p>Information not available</p>"
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
html_content = requests.get(artworkdescriptioncontenturl).text
# html_content = requests.get(artworkdescriptioncontenturl).text
# Parse the html content
soup = BeautifulSoup(html_content, "lxml")
# 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("div" , {"class" : "mw-parser-output"})
# text=soup.find_all("p")
artworkdescriptiontext=Markup(text)
# artworkdescriptiontext=Markup(text)
print(artworkdescriptiontext)
# print(artworkdescriptiontext)
############ right bottom LATER
# exhibitions + id to be changed

Loading…
Cancel
Save