Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added Codeforces Contest Schedule/data #1014

Merged
merged 3 commits into from
May 19, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 4 additions & 7 deletions dev-documentation.md
Original file line number Diff line number Diff line change
Expand Up @@ -1635,13 +1635,12 @@ olympics = Olympics()

## Codeforces

Create an instance of `Users` class
Create an instance of `Codeforces` class

```python
from scrape_up import codeforces

codeforces_user = codeforces.Users(username="tourist")
codeforces_user.get_user_data()
codeforces = Codeforces()
```

Methods
Expand All @@ -1650,6 +1649,7 @@ Methods
| Methods | Details |
| -------------------------- | ---------------------------------- |
| `.get_user_data(username)` | Fetches user data from CodeForces. |
| `get_contests()` | Returns information on contests. |
```

---
Expand Down Expand Up @@ -1745,9 +1745,7 @@ result = steam.ScrapeGames(n0Games=5, tags=["Discounts", "F2P"])
| ----------------------------- | ------------------------------------------- |
| `.ScrapeGames(n0Games, tags)` | Scrapes game data for each specified filter |


-------

---

## Lichess

Expand Down Expand Up @@ -1853,4 +1851,3 @@ trek=Indiantrekking("hidden-lakes-of-kashmir")
| `outline_day_to_day_itinerary` | returns the ouline of the day to day itinerary |

---

3 changes: 1 addition & 2 deletions src/scrape_up/ambitionBox/company.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@

# import requests
# from bs4 import BeautifulSoup

Expand Down Expand Up @@ -78,4 +77,4 @@

# if __name__ == "__main__":
# c = Comapiens(10)
# c.scrape_companies()
# c.scrape_companies()
4 changes: 4 additions & 0 deletions src/scrape_up/codeforces/__init__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
from .user import Users
from .contests import Contest

__all__ = ["Users", "Contest"]
84 changes: 84 additions & 0 deletions src/scrape_up/codeforces/contests.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,84 @@
from bs4 import BeautifulSoup
import json
from scrape_up.config.request_config import RequestConfig, get


class Contest:
"""
First, create an object of class `Contest`

```python
codeforces = Contest()
```

| Methods | Details |
| ---------------------------- | ----------------------------------------------------------------------------------------- |
| `get_contests()` | Returns information on active contests like title, start, and duration |
"""

def __init__(self, *, config: RequestConfig = RequestConfig()):
headers = {"User-Agent": "scrapeup"}
self.config = config
if self.config.headers == {}:
self.config.set_headers(headers)

def get_contests(self):
"""
Method to fetch the list of active contests on Codeforces using web scraping.

Example
-------
```python
codeforces = Contest()
codeforces.get_contests()
```

Returns
-------
{
"data": [
{
"name": "Codeforces Round #731 (Div. 3)",
"start": "Aug/08/2021 17:35",
"length": "2 hrs"
},
...
],
"message": "Found contest list"
}
"""
codeforces_url = "https://codeforces.com/contests"
response = get(codeforces_url, self.config)

if response.status_code != 200:
json.dumps({"data": None, "message": "Cannot load Contest"})

soup = BeautifulSoup(response.text, "html.parser")
contest_list = []

try:

upcoming_contests = soup.find("div", {"class": "datatable"}).find_all("tr")
for contest in upcoming_contests:
columns = contest.find_all("td")
if len(columns) == 6:
name = columns[0].text.strip()
start_time_str = columns[2].text.strip()
duration_str = columns[3].text.strip()

name = " ".join(
line.strip() for line in name.splitlines() if line.strip()
)
name = name.replace("Enter »", "").strip()

contest_list.append(
{
"name": name,
"start": start_time_str,
"length": duration_str,
}
)

return contest_list
except Exception:
return None
2 changes: 1 addition & 1 deletion src/scrape_up/indiantrekking/trek.py
Original file line number Diff line number Diff line change
Expand Up @@ -59,4 +59,4 @@ def outline_day_to_day_itinerary(self):
outline = self.soup.find("div", class_="itinerary").text
return outline
except:
return None
return None
5 changes: 2 additions & 3 deletions src/scrape_up/lichess/lichess.py
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ def __fetch_page_games(self, page_num):
game_list.append(game_info)
return game_list

def fetch_games(self,start_page=1,end_page=4):
def fetch_games(self, start_page=1, end_page=4):
"""
Fetch all the games data for the specified username.

Expand All @@ -53,7 +53,7 @@ def fetch_games(self,start_page=1,end_page=4):
```python
# Default usage:
games = scraper.fetch_games()

# Custom usage:
games = scraper.fetch_games(start_page=5, end_page=8)
```
Expand Down Expand Up @@ -130,4 +130,3 @@ def __get_pgn(self, game_data):
pgn_request = requests.get(f"https://lichess.org{gameUrl}")._content
parsed_pgn = BeautifulSoup(pgn_request, "lxml")
return parsed_pgn.find("div", {"class": "pgn"}).text