Heroic_verse / src /app.py
jayanth-2005's picture
Update src/app.py
48e47aa verified
Raw History Blame Contribute Delete
10.1 kB
import streamlit as st
import requests
from PIL import Image, UnidentifiedImageError
from io import BytesIO
from googletrans import Translator
# --- Page Setup ---
st.set_page_config(page_title="🧘 HeroicVerse: Freedom Fighters Explorer", layout="wide")
st.title("🧘 HeroicVerse: Discover Global Freedom Fighters")
st.write("Explore inspiring stories, biographies, and images of freedom fighters using Wikimedia APIs.")
# --- Shared request setup ---
# Wikimedia's API etiquette policy requires a descriptive User-Agent.
# Requests without one are frequently throttled/blocked, which can come
# back as an HTML page instead of JSON and crash `.json()` parsing.
HEADERS = {
"User-Agent": "HeroicVerse/1.0 (https://example.com/contact; contact@example.com)"
}
REQUEST_TIMEOUT = 10 # seconds
def safe_get_json(url, params=None):
"""GET a URL and safely parse JSON, returning (data, error_message)."""
try:
response = requests.get(url, params=params, headers=HEADERS, timeout=REQUEST_TIMEOUT)
except requests.exceptions.RequestException as e:
return None, f"Network error while contacting {url}: {e}"
if response.status_code != 200:
return None, f"Request to {url} failed with status {response.status_code}."
content_type = response.headers.get("Content-Type", "")
if "application/json" not in content_type:
return None, (
f"Expected JSON from {url} but got '{content_type}'. "
f"This usually means the request was blocked, rate-limited, "
f"or the endpoint returned an error page."
)
try:
return response.json(), None
except requests.exceptions.JSONDecodeError:
return None, f"Could not decode JSON from {url} (empty or malformed response)."
# --- Translator Setup ---
translator = Translator()
language_options = {
"English": "en",
"Hindi": "hi",
"Telugu": "te",
"Tamil": "ta",
"Bengali": "bn"
}
selected_lang = st.selectbox("🌐 Choose language", list(language_options.keys()))
lang_code = language_options[selected_lang]
# --- Caching Functions ---
@st.cache_data(show_spinner=False)
def fetch_wikipedia_summary(name):
search_url = "https://en.wikipedia.org/w/api.php"
params = {
"action": "query", "list": "search", "srsearch": name, "format": "json"
}
res, err = safe_get_json(search_url, params)
if err:
return None, name, err
results = res.get("query", {}).get("search", [])
if not results:
return None, name, None
exact_title = results[0]["title"]
summary_url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{exact_title.replace(' ', '_')}"
summary_data, summary_err = safe_get_json(summary_url)
if summary_err:
return None, exact_title, summary_err
return summary_data, exact_title, None
@st.cache_data(show_spinner=False)
def fetch_wikidata_info(name):
search_url = "https://www.wikidata.org/w/api.php"
params = {
"action": "wbsearchentities", "language": "en", "format": "json", "search": name
}
res, err = safe_get_json(search_url, params)
if err or not res:
return {}, err
if res.get("search"):
entity_id = res["search"][0]["id"]
entity_url = f"https://www.wikidata.org/wiki/Special:EntityData/{entity_id}.json"
entity_data, entity_err = safe_get_json(entity_url)
if entity_err or not entity_data:
return {}, entity_err
return entity_data.get("entities", {}).get(entity_id, {}), None
return {}, None
@st.cache_data(show_spinner=False)
def fetch_commons_images(name):
url = "https://commons.wikimedia.org/w/api.php"
params = {
"action": "query", "format": "json", "generator": "search",
"gsrsearch": f"file:{name}", "gsrlimit": 5,
"prop": "imageinfo", "iiprop": "url", "iiurlwidth": 400
}
res, err = safe_get_json(url, params)
if err or not res:
return [], err
pages = res.get("query", {}).get("pages", {})
return [p["imageinfo"][0]["thumburl"] for p in pages.values() if "imageinfo" in p], None
@st.cache_data(show_spinner=False)
def fetch_image_bytes(url):
try:
response = requests.get(url, headers=HEADERS, timeout=REQUEST_TIMEOUT)
response.raise_for_status()
return response.content, None
except requests.exceptions.RequestException as e:
return None, str(e)
# --- Helper Functions ---
def translate_text(text, lang):
try:
return translator.translate(text, dest=lang).text
except Exception:
return text
def translate_to_english(text):
try:
return translator.translate(text, dest="en").text
except Exception:
return text
def extract_ids(entity, prop):
return [
c.get("mainsnak", {}).get("datavalue", {}).get("value", {}).get("id", "")
for c in entity.get("claims", {}).get(prop, [])
if c.get("mainsnak", {}).get("datatype") == "wikibase-item"
]
# --- User Input ---
user_input = st.text_input("πŸ” Enter the name of a Freedom Fighter", "Mahatma Gandhi")
name_local = user_input.strip()
name_english = translate_to_english(name_local).title() if name_local else ""
if name_english:
summary_en, title_en, summary_err = fetch_wikipedia_summary(name_english)
if summary_err:
st.error(f"Couldn't fetch Wikipedia data: {summary_err}")
st.stop()
entity, entity_err = fetch_wikidata_info(title_en)
if entity_err:
st.warning(f"Couldn't fetch Wikidata info: {entity_err}")
entity = {}
occ_ids = extract_ids(entity, "P106")
role_ids = extract_ids(entity, "P39")
move_ids = extract_ids(entity, "P135")
all_roles = set(occ_ids + role_ids + move_ids)
freedom_roles = {
"Q82955", "Q829982", "Q152968", "Q177220",
"Q1219475", "Q9134", "Q37226", "Q327055", "Q844253"
}
label = entity.get("labels", {}).get("en", {}).get("value", "").lower()
desc = entity.get("descriptions", {}).get("en", {}).get("value", "").lower()
summary_text = summary_en.get('extract', '').lower() if summary_en else ""
text_block = f"{label} {desc} {summary_text}"
keywords = ["freedom fighter", "revolutionary", "independence", "anti-colonial", "civil rights", "nationalist"]
is_freedom_fighter = bool(freedom_roles.intersection(all_roles)) or any(kw in text_block for kw in keywords)
if not is_freedom_fighter:
st.error(f"\"{name_local}\" is not classified as a freedom fighter. Please try another name.")
else:
tabs = st.tabs(["Summary", "Biography", "Gallery"])
with tabs[0]:
st.subheader(f"πŸ““ {translate_text('Summary of', lang_code)} {translate_text(title_en, lang_code)}")
if summary_en:
st.markdown(f"**{translate_text('Title', lang_code)}**: {translate_text(summary_en.get('title', ''), lang_code)}")
st.markdown(f"**{translate_text('Description', lang_code)}**: {translate_text(summary_en.get('description', ''), lang_code)}")
st.write(translate_text(summary_en.get('extract', ''), lang_code))
if summary_en.get('thumbnail'):
st.markdown(f"<div style='text-align:center'><img src='{summary_en['thumbnail']['source']}' width='200'></div>", unsafe_allow_html=True)
claims = entity.get("claims", {})
def get_date(prop):
v = claims.get(prop, [{}])[0].get("mainsnak", {}).get("datavalue", {}).get("value", {})
return v.get('time', '')[1:11]
dob = get_date('P569')
dod = get_date('P570')
if dob:
st.markdown(f"**πŸ“… {translate_text('Born', lang_code)}:** {dob}")
if dod:
st.markdown(f"**🚦 {translate_text('Died', lang_code)}:** {dod}")
else:
st.warning(translate_text("No summary available.", lang_code))
with tabs[1]:
st.subheader(f"πŸ“œ {translate_text('Biography of', lang_code)} {translate_text(title_en, lang_code)}")
bio_params = {
"action": "query", "prop": "extracts", "titles": title_en,
"format": "json", "explaintext": True, "exsectionformat": "plain"
}
bio_res, bio_err = safe_get_json("https://en.wikipedia.org/w/api.php", bio_params)
if bio_err:
st.warning(f"Couldn't fetch biography: {bio_err}")
bio = ""
else:
pages = bio_res.get("query", {}).get("pages", {})
bio = next(iter(pages.values())).get('extract', '') if pages else ""
lines = bio.replace('\n\n', '\n').split('\n')
key = [l for l in lines if any(k in l.lower() for k in ['born', 'independence', 'leader', 'movement', 'education', 'death', 'civil rights'])]
if key:
for l in key:
st.markdown(f"**{translate_text(l.strip(), lang_code)}**")
else:
st.warning(translate_text("No key biography points found.", lang_code))
with tabs[2]:
st.subheader(f"πŸ–Ό {translate_text('Gallery of', lang_code)} {translate_text(title_en, lang_code)}")
imgs, imgs_err = fetch_commons_images(title_en)
if imgs_err:
st.warning(f"Couldn't fetch gallery: {imgs_err}")
if imgs:
for url in imgs:
img_bytes, dl_err = fetch_image_bytes(url)
if dl_err or img_bytes is None:
st.warning(f"Could not load image from {url}")
continue
try:
img = Image.open(BytesIO(img_bytes))
st.image(img, width=300)
except UnidentifiedImageError:
st.warning(f"Could not load image from {url}")
else:
st.warning(translate_text("No images found.", lang_code))