From 739fcb5f93ebf1791a9a58a2903a3b35ad2fe0f0 Mon Sep 17 00:00:00 2001
From: dominip89 <dominip89@mi.fu-berlin.de>
Date: Sun, 23 May 2021 17:55:33 +0000
Subject: [PATCH] Update course_scraper.py
---
unisportomat/course_scraper/course_scraper.py | 17 +++++++++++++----
1 file changed, 13 insertions(+), 4 deletions(-)
diff --git a/unisportomat/course_scraper/course_scraper.py b/unisportomat/course_scraper/course_scraper.py
index 27ea1ce..2d51c7f 100644
--- a/unisportomat/course_scraper/course_scraper.py
+++ b/unisportomat/course_scraper/course_scraper.py
@@ -1,3 +1,8 @@
+"""
+Implementation of a rudementary scraping tool
+for http://www.buchsys.de for SWP UniSport-O-Mat.
+"""
+
import requests
from bs4 import BeautifulSoup
@@ -17,17 +22,21 @@ def fetch_website(url):
# pinpoint the parser only to the section containing the course names and links
return soup.find("dl", {"class": "bs_menu"}).find_all("a", href=True)
- except requests.exceptions.RequestException as e:
- print(e)
+ except requests.exceptions.RequestException as err:
+ print(err)
+ raise
def scraping(site=None) -> dict:
"""
- Returns a dictionary of the form {name: link}, containing the scraped content of https://www.buchsys.de/fu-berlin/angebote/aktueller_zeitraum/index.html, unless another URL is given as an argument.
+ Returns a dictionary of the form {name: link},
+ containing the scraped content of
+ https://www.buchsys.de/fu-berlin/angebote/aktueller_zeitraum/index.html,
+ unless another URL is given as an argument.
"""
courses = {}
- if site == None:
+ if site is None:
site = "https://www.buchsys.de/fu-berlin/angebote/aktueller_zeitraum/"
website = fetch_website(site)
--
GitLab