ycombinator-parser/yc_streamlight_app.py at main · iMCrazyDev/ycombinator-parser · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
import streamlit as st
import pandas as pd
import time
from yc_enrich import fetch_all_companies_s25, extract_linkedin_url, check_yc_mention

st.set_page_config(page_title="YC S25 Live Parser", layout="wide")
st.title("Y Combinator Summer 2025 — Live Parsing")
st.caption("Companies appear below as soon as they are processed.")

if "df" not in st.session_state:
    st.session_state.df = pd.DataFrame(columns=[
        "Name", "Website", "YC Page", "LinkedIn", "YC S25 on LinkedIn"
    ])
if "seen_slugs" not in st.session_state:
    st.session_state.seen_slugs = set()

if st.button("Start live parsing"):
    placeholder = st.empty()
    progress_bar = st.progress(0, text="Fetching company list…")

    with st.spinner("Downloading company list from Algolia…"):
        all_companies = fetch_all_companies_s25()

    total = len(all_companies)
    progress_bar.progress(0, text=f"0 / {total} parsed")

    for i, company in enumerate(all_companies, start=1):
        slug = company.get("slug")
        if slug in st.session_state.seen_slugs:
            progress_bar.progress(i / total, text=f"{i} / {total} skipped dup")
            continue
        st.session_state.seen_slugs.add(slug)

        name = company.get("name")
        website = company.get("website")
        yc_url = f"https://www.ycombinator.com/companies/{slug}"

        linkedin_url = extract_linkedin_url(slug)
        yc_s25_flag = check_yc_mention(linkedin_url) if linkedin_url else None

        st.session_state.df.loc[len(st.session_state.df)] = {
            "Name": name,
            "Website": website,
            "YC Page": yc_url,
            "LinkedIn": linkedin_url,
            "YC S25 on LinkedIn": yc_s25_flag
        }

        placeholder.dataframe(st.session_state.df, use_container_width=True)
        progress_bar.progress(i / total, text=f"{i} / {total} parsed")
        time.sleep(0.3)

    st.session_state.df.drop_duplicates(subset="YC Page", inplace=True, ignore_index=True)
    progress_bar.empty()
    st.success("Parsing completed")

if not st.session_state.df.empty:
    st.download_button(
        "Download CSV",
        data=st.session_state.df.to_csv(index=False),
        file_name="yc_s25_live.csv",
        mime="text/csv",
        key="download-yc-s25"
    )