1
0
Fork 0
mirror of https://github.com/SocksPls/hltv-api synced 2025-04-30 15:43:07 +00:00

refactored bs4 parsing pages

This commit is contained in:
flannel jesus 2016-09-11 23:40:54 +01:00
parent b49abe92fa
commit 3fc083b5e3

13
main.py
View file

@ -2,24 +2,24 @@ import requests
import json
from bs4 import BeautifulSoup
home = requests.get("http://hltv.org/").text
home = BeautifulSoup(home, "lxml")
matches = requests.get("http://www.hltv.org/matches/").text
matches = BeautifulSoup(matches, "lxml")
def get_parsed_page(url):
return BeautifulSoup(requests.get(url).text, "lxml")
def top5teams():
home = get_parsed_page("http://hltv.org/")
count = 0
teams = []
for team in home.find_all("div", {"class": "vsbox",})[:5]:
for team in home.find_all("div", {"class": "vsbox", })[:5]:
count += 1
teamname = team.find_all("div")[2].text.strip()
teams.append(teamname)
return teams
def getmatches():
match_data = []
matches = get_parsed_page("http://www.hltv.org/matches/")
matchlist = matches.find_all("div", {"class": ["matchListBox", "matchListDateBox"]})
for match in matchlist:
if match['class'][0] == "matchListDateBox":
@ -33,5 +33,6 @@ def getmatches():
except:
print(match.text[:7].strip(), match.text[7:-7].strip())
if __name__ == "__main__":
getmatches()