IsaacShoebottom/KingsLandingJobScraper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: IsaacShoebottom:7f9cac6be85f4483c2efd7b28ade6b30cdd579ad
Branches Tags
IsaacShoebottom:master
...
compare: IsaacShoebottom:master
Branches Tags
IsaacShoebottom:master

3 Commits
7f9cac6be8 ... master

Author SHA1 Message Date
Isaac Shoebottom
adf8b5e22e Change testing to false 2023-01-31 19:55:09 -04:00
Isaac Shoebottom
74518bc568 Add discord config 2023-01-25 23:11:31 -04:00
Isaac Shoebottom
ae9033ebff Add comments about improvments 2023-01-25 23:11:21 -04:00
2 changed files with 13 additions and 1 deletions
Expand all files Collapse all files

7
.idea/discord.xml generated Normal file
View File

@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="DiscordProjectSettings">
<option name="show" value="ASK" />
<option name="description" value="" />
</component>
</project>

7
scraper.py
View File

@ -9,6 +9,11 @@ from bs4 import BeautifulSoup
# Made for a friend with love # Made for a friend with love
# Tested with Python 3.10.7 on Windows 10 # Tested with Python 3.10.7 on Windows 10
# TODO: Look into using requests, urllib3, and/or selenium to scrape the page
# https://pypi.org/project/selenium/
# https://pypi.org/project/urllib3/
# https://pypi.org/project/requests/
def scrape(): def scrape():
contents = urllib.request.urlopen("https://kingslanding.nb.ca/employment/").read() contents = urllib.request.urlopen("https://kingslanding.nb.ca/employment/").read()
soup = BeautifulSoup(contents, "html.parser") soup = BeautifulSoup(contents, "html.parser")
@ -28,7 +33,7 @@ def scrape():
if __name__ == '__main__': if __name__ == '__main__':
testing = True testing = False
will_exit = False will_exit = False
hours = 3 hours = 3