sisters in sweat.

Makefile

@@ -132,9 +132,8 @@ out/aceofpubs.json: out/aceofpubs.ics
 out/koota.txt:
 	curl_chrome116 --silent "https://courtyardkoota.com/event-directory/" | grep -oE 'https://courtyardkoota\.com/events/[a-z0-9-]+/' | sort -u > $@ || $(call restore-file,$@)
 
-# TODO
-# out/sis.txt:
-# 	python src/sis.py | sort > out/sis.txt
+out/sis.json:
+	python src/sis.py || $(call restore-file,$@)
 
 fetch: out/allevents.txt \
  out/highape.txt \
@@ -166,7 +165,8 @@ fetch: out/allevents.txt \
  out/atta_galatta.json \
  out/koota.txt \
  out/te.json \
- out/underline.json
+ out/underline.json \
+ out/sis.json
 
 	@echo "Done"
 

src/event-fetcher.py

@@ -50,7 +50,8 @@
     "out/venn.json",  # this also has a lot of duplicates
     "out/te.json",
     "out/zomato.json",
-    "out/underline.json" # duplicates to insider
+    "out/underline.json", # duplicates to insider
+    "out/sis.json"
 ]
 
 KNOWN_EVENT_TYPES = [

src/gullytours.py

@@ -92,5 +92,4 @@ def read_config():
 
 
 if __name__ == "__main__":
-
     main()

src/sis.py

@@ -1,38 +1,99 @@
 from bs4 import BeautifulSoup
-from common.session import get_cached_session
+# from common.session import get_cached_session
+import requests
+from common.tz import IST
 import json
 import datetime
 import re
 import os
 from urllib.parse import urlencode
+import datefinder
+BASE_URL = "https://sistersinsweat.in"
 
-
-def fetch_events_html():
-    session = get_cached_session()
-    response = session.get("https://sistersinsweat.in/events?city=4")
+def fetch_events_html(session):
+    response = session.get(BASE_URL + "/events?city=4")
     return response.text
 
+def fix_date(date_str):
+    return date_str.replace(" ", "T") + "+05:30"
+
+def fetch_ajax_details(sku, _token):
+    data = {
+        "_token": _token,
+        "sku": sku,
+        "location_name": "4"
+    }
+    url = BASE_URL + "/getTimeSlotAjax"
+    e = session.post(url, data=data).json()[0]
+
+    return {
+        "startDate": fix_date(e['start_date']),
+        "endDate": fix_date(e['end_date']),
+        "offers": [{
+            "price": e['price'],
+            "priceCurrency": "INR"
+        }]
+    }
 
-def read_events_html():
-    with open("fixtures/sisters-in-sweat.html", "r") as f:
-        return f.read()
 
+def fetch_event_details(session, l):
 
-def fetch_event_details(l):
-    session = get_cached_session()
     response = session.get(l)
     html = response.text
     soup = BeautifulSoup(html, "html.parser")
-    div = soup.select_one("#description").text.replace("\n\n", "\n")
-    print(div)
-
+    div = soup.select_one("#description")
+    event = {
+        "name": soup.select_one('h2').text,
+        "@type": "SocialEvent",
+        "url": l,
+        "@context": "https://schema.org",
+        "keywords": ["SISTERSINSWEAT"],
+        "audience": {
+            "@type": "Audience",
+            "AudienceType": "Women-only event"
+        },
+        "eventAttendanceMode": "OfflineEventAttendanceMode",
+        "eventStatus": "EventScheduled",
+        "inLanguage": "en",
+        "organizer": {
+            "@type": "Organization",
+            "name": "Sisters In Sweat",
+            "url": "https://sistersinsweat.in"
+        }
+    }
+    if div:
+        text = div.text.replace("\n\n", "\n")
+        event['description'] = text
+    img = soup.select_one('img.img-fluid')
+    if img:
+        event['image'] = img.get('src')
+    v = soup.select_one('#venue')
+    if v:
+        venue_text = v.text
+        s = venue_text.split("-")
+        venue_text  = s[0].strip()
+        venue_address = " ".join(s[1:])
+        event['location'] = {
+            "name": venue_text,
+            "address": venue_address,
+            "type": "Place"
+        }
+    sku = soup.select_one('input[name="sku"]').get('value')
+    _token = soup.select_one('input[name="_token"]').get('value')
+    event = event  | fetch_ajax_details(sku, _token)
+    return event
 
 def fetch_events_links(html):
     soup = BeautifulSoup(html, "html.parser")
     links = soup.select('a[href^="https://sistersinsweat.in/session_details/"]')
     return [link.get("href") for link in links]
 
-
-html = read_events_html()
-for l in fetch_events_links(html):
-    fetch_event_details(l)
+if __name__ == "__main__":
+    session = requests.Session() # get_cached_session()
+    html = fetch_events_html(session)
+    events = []
+    for l in fetch_events_links(html):
+        e = fetch_event_details(session, l)
+        events.append(e)
+    with open("out/sis.json", "w") as f:
+        json.dump(events, f, indent=2)