Spaces:
Starting
Starting
fresh start
Browse files- .gitattributes +35 -0
- .gitignore +3 -0
- Dockerfile +2 -9
- README.md +8 -14
- main.py → app.py +35 -31
- requirements.txt +3 -4
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
.venv/
|
| 2 |
+
|
| 3 |
+
*.pyc*
|
Dockerfile
CHANGED
|
@@ -6,17 +6,10 @@ USER root
|
|
| 6 |
|
| 7 |
COPY ./requirements.txt /code/requirements.txt
|
| 8 |
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
RUN /install.sh && rm /install.sh
|
| 12 |
-
|
| 13 |
-
RUN /root/.cargo/bin/uv pip install --system --no-cache -r requirements.txt
|
| 14 |
|
| 15 |
COPY . /code
|
| 16 |
|
| 17 |
USER user
|
| 18 |
|
| 19 |
-
|
| 20 |
-
# CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:get_repos()"]
|
| 21 |
-
# CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]
|
| 22 |
-
CMD ["flask", "run", "--host", "0.0.0.0", "--port", "7860"]
|
|
|
|
| 6 |
|
| 7 |
COPY ./requirements.txt /code/requirements.txt
|
| 8 |
|
| 9 |
+
RUN pip install -r requirements.txt
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
COPY . /code
|
| 12 |
|
| 13 |
USER user
|
| 14 |
|
| 15 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
|
|
|
|
|
|
|
|
README.md
CHANGED
|
@@ -1,14 +1,8 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
• Python
|
| 10 |
-
• Flask
|
| 11 |
-
• BeautifulSoup4
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
Deployed Link: https://arpy8-github-repo-scraper.hf.space/
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: HackProjects Server
|
| 3 |
+
emoji: 😜
|
| 4 |
+
colorFrom: red
|
| 5 |
+
colorTo: blue
|
| 6 |
+
sdk: docker
|
| 7 |
+
pinned: false
|
| 8 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
main.py → app.py
RENAMED
|
@@ -1,25 +1,34 @@
|
|
|
|
|
| 1 |
import bs4
|
| 2 |
-
import json
|
| 3 |
import requests
|
| 4 |
-
from
|
| 5 |
-
from
|
| 6 |
|
| 7 |
-
app =
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
LANGUAGES = ["python", "javascript", "html", "typescript", "java", "cpp", "php", "go", "css", "c"]
|
| 11 |
|
| 12 |
-
def fetch_github_page(**kwargs):
|
| 13 |
try:
|
| 14 |
params = '&'.join([f'{k}={v}' for k, v in kwargs.items()])
|
| 15 |
url = 'https://github.com/topics/hacktoberfest?{}'.format(params)
|
| 16 |
response = requests.get(url)
|
| 17 |
response.raise_for_status()
|
| 18 |
-
|
|
|
|
|
|
|
| 19 |
except requests.RequestException as e:
|
| 20 |
-
|
| 21 |
|
| 22 |
-
def parse_repositories(page_content):
|
| 23 |
soup = bs4.BeautifulSoup(page_content, 'html.parser')
|
| 24 |
articles = soup.find_all("article")
|
| 25 |
repositories = []
|
|
@@ -30,44 +39,39 @@ def parse_repositories(page_content):
|
|
| 30 |
if len(repo_info) >= 3 and "Star" in repo_info[2]:
|
| 31 |
owner = repo_info[0]
|
| 32 |
repo_name = repo_info[1]
|
| 33 |
-
stars = repo_info[2]
|
| 34 |
-
repo_link = f"https://github.com/{owner}/{repo_name}"
|
| 35 |
|
| 36 |
repositories.append({
|
| 37 |
"repo": repo_name,
|
| 38 |
"owner": owner,
|
| 39 |
"stars": stars,
|
| 40 |
-
"link": repo_link
|
| 41 |
})
|
| 42 |
|
| 43 |
return repositories
|
| 44 |
|
| 45 |
-
@app.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
def get_all_repos():
|
| 47 |
-
payload = {}
|
| 48 |
-
|
| 49 |
for lang in LANGUAGES:
|
| 50 |
page_content = fetch_github_page(l=lang)
|
| 51 |
-
|
| 52 |
-
if isinstance(page_content, str) and page_content.startswith("Error"):
|
| 53 |
-
return page_content
|
| 54 |
-
|
| 55 |
repositories = parse_repositories(page_content)
|
| 56 |
payload[lang] = repositories
|
| 57 |
-
|
| 58 |
-
print(payload)
|
| 59 |
-
|
| 60 |
-
return json.dumps(payload, indent=4)
|
| 61 |
|
| 62 |
-
|
| 63 |
-
def get_repos(lang):
|
| 64 |
-
page_content = fetch_github_page(l=lang)
|
| 65 |
-
if isinstance(page_content, str) and page_content.startswith("Error"):
|
| 66 |
-
return page_content
|
| 67 |
|
|
|
|
|
|
|
|
|
|
| 68 |
repositories = parse_repositories(page_content)
|
| 69 |
-
|
|
|
|
| 70 |
|
| 71 |
|
| 72 |
-
if __name__
|
| 73 |
-
|
|
|
|
|
|
| 1 |
+
from typing import Dict, List, Any
|
| 2 |
import bs4
|
|
|
|
| 3 |
import requests
|
| 4 |
+
from fastapi import FastAPI, HTTPException
|
| 5 |
+
from fastapi.middleware.cors import CORSMiddleware
|
| 6 |
|
| 7 |
+
app = FastAPI()
|
| 8 |
+
|
| 9 |
+
app.add_middleware(
|
| 10 |
+
CORSMiddleware,
|
| 11 |
+
allow_origins=["*"],
|
| 12 |
+
allow_credentials=True,
|
| 13 |
+
allow_methods=["*"],
|
| 14 |
+
allow_headers=["*"],
|
| 15 |
+
)
|
| 16 |
|
| 17 |
LANGUAGES = ["python", "javascript", "html", "typescript", "java", "cpp", "php", "go", "css", "c"]
|
| 18 |
|
| 19 |
+
def fetch_github_page(**kwargs) -> str:
|
| 20 |
try:
|
| 21 |
params = '&'.join([f'{k}={v}' for k, v in kwargs.items()])
|
| 22 |
url = 'https://github.com/topics/hacktoberfest?{}'.format(params)
|
| 23 |
response = requests.get(url)
|
| 24 |
response.raise_for_status()
|
| 25 |
+
|
| 26 |
+
return response.text
|
| 27 |
+
|
| 28 |
except requests.RequestException as e:
|
| 29 |
+
raise HTTPException(status_code=502, detail=f"Error fetching data: {e}")
|
| 30 |
|
| 31 |
+
def parse_repositories(page_content: str) -> List[Dict[str, Any]]:
|
| 32 |
soup = bs4.BeautifulSoup(page_content, 'html.parser')
|
| 33 |
articles = soup.find_all("article")
|
| 34 |
repositories = []
|
|
|
|
| 39 |
if len(repo_info) >= 3 and "Star" in repo_info[2]:
|
| 40 |
owner = repo_info[0]
|
| 41 |
repo_name = repo_info[1]
|
| 42 |
+
stars = repo_info[2][6:-1] if repo_info[2].startswith("Star\n") else repo_info[2]
|
|
|
|
| 43 |
|
| 44 |
repositories.append({
|
| 45 |
"repo": repo_name,
|
| 46 |
"owner": owner,
|
| 47 |
"stars": stars,
|
|
|
|
| 48 |
})
|
| 49 |
|
| 50 |
return repositories
|
| 51 |
|
| 52 |
+
@app.get("/")
|
| 53 |
+
def index():
|
| 54 |
+
return {"name": "github repo scraper", "author": "arpy8"}
|
| 55 |
+
|
| 56 |
+
@app.get("/all")
|
| 57 |
def get_all_repos():
|
| 58 |
+
payload: Dict[str, Any] = {}
|
| 59 |
+
|
| 60 |
for lang in LANGUAGES:
|
| 61 |
page_content = fetch_github_page(l=lang)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
repositories = parse_repositories(page_content)
|
| 63 |
payload[lang] = repositories
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
|
| 65 |
+
return payload
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
|
| 67 |
+
@app.get("/data/{lang}")
|
| 68 |
+
def get_repos(lang: str):
|
| 69 |
+
page_content = fetch_github_page(l=lang)
|
| 70 |
repositories = parse_repositories(page_content)
|
| 71 |
+
|
| 72 |
+
return repositories
|
| 73 |
|
| 74 |
|
| 75 |
+
if __name__=="__main__":
|
| 76 |
+
import uvicorn
|
| 77 |
+
uvicorn.run(app)
|
requirements.txt
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
-
|
|
|
|
| 2 |
beautifulsoup4==4.12.3
|
| 3 |
requests==2.32.3
|
| 4 |
-
html5lib==1.1
|
| 5 |
-
flask-cors==5.0.0
|
| 6 |
-
gunicorn
|
|
|
|
| 1 |
+
fastapi==0.95.2
|
| 2 |
+
uvicorn[standard]==0.22.0
|
| 3 |
beautifulsoup4==4.12.3
|
| 4 |
requests==2.32.3
|
| 5 |
+
html5lib==1.1
|
|
|
|
|
|