primary site for this project: https://tracker.gg/lol

This crawler is built using selenium using the firefox webdriver

In [1]:

from selenium import webdriver
from selenium.webdriver.firefox.service import Service as FirefoxService
from webdriver_manager.firefox import GeckoDriverManager
from selenium.webdriver.common.by import By

In [2]:

driver = webdriver.Firefox(service=FirefoxService(GeckoDriverManager().install()))

driver.get("https://tracker.gg/lol/leaderboards/stats/all/LeaguePoints?region=NA&queueType=RANKED_SOLO_5x5")

driver.implicitly_wait(3)

[WDM] - Downloading: 19.0kB [00:00, 2.11MB/s]

North America Leaderboard

In [3]:

na_leaderboard = driver.find_elements(By.TAG_NAME, 'tr')

In [4]:

# python lists to store data

overall_position = []
player_name = []
rank = []
league_points = []
win_rate = []
matches_played = []

In [5]:

for player in na_leaderboard:

    new_list = player.text.split()

    if len(new_list) == 6:

        overall_position.append(new_list[0])
        player_name.append(new_list[1])
        rank.append(new_list[2])
        league_points.append(new_list[3])
        win_rate.append(new_list[4])
        matches_played.append(new_list[5])

    elif len(new_list) == 7:

        two_name_player = new_list[1] + new_list[2]

        overall_position.append(new_list[0])
        player_name.append(two_name_player)
        rank.append(new_list[3])
        league_points.append(new_list[4])
        win_rate.append(new_list[5])
        matches_played.append(new_list[6])

    elif len(new_list) == 8:

        three_name_player = new_list[1] + new_list[2] + new_list[3]

        overall_position.append(new_list[0])
        player_name.append(three_name_player)
        rank.append(new_list[4])
        league_points.append(new_list[5])
        win_rate.append(new_list[6])
        matches_played.append(new_list[7])

print(overall_position)
print(player_name)
print(rank)
print(league_points)
print(win_rate)
print(matches_played)

['5', '7', '8', '13', '14', '17', '18', '18', '21', '23', '26', '27', '31', '34', '37', '39', '48', '48', '61', '65', '66', '68', '72', '75', '75', '77', '82', '82', '84', '89', '89', '94', '95', '96']
['Nim', 'Neo', 'NIKJOJO', 'noinvade', 'Not', 'niewang', 'nathanwemiss', 'NALCS', 'NaCl', 'MónkeyD', 'noones', 'neopets', 'Notorious', 'nodravenday', 'No', 'newbury', 'Nice', 'Ninja', 'Not', 'Nostalgia', 'Never', 'no1care', 'NIGHTMARE', 'Need', 'Niek', 'Nickji', 'navel', 'Mystical', 'NOOB', 'not', 'MySensei', 'Not', 'NanoSpeck', 'NiMama']
['Chimpsky', 'NanChangGodE', '1', 'pls', 'Hans', 'zii', 'u', 'YI', 'Tim', 'Luffy', 'fault', 'lover', 'Malli', '1', 'Focus', 'park', 'Bunz', 'Doggy', 'Viable', 'Lee', 'Story', 'me', 'BABY', 'Therapy', 'Joel', '18', 'orange', 'Firefly', 'Fredy41OO', 'skip', 'PzZzang', 'aIöne', 'v2', 'Boom']
['Challenger', 'Grandmaster', 'Grandmaster', 'Grandmaster', 'Grandmaster', 'Grandmaster', 'Grandmaster', 'Grandmaster', 'Grandmaster', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master', 'Master']
['954', '822', '802', '658', '637', '557', '552', '552', '547', '509', '435', '433', '379', '345', '309', '308', '211', '211', '93', '75', '73', '65', '45', '44', '44', '36', '29', '29', '23', '18', '18', '13', '2', '1']
['0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%', '0%']

In [6]:

# check if lists are empty

assert (overall_position != []), 'list is empty'
assert (player_name != []), 'list is empty'
assert (rank != []), 'list is empty'
assert (league_points != []), 'list is empty'
assert (win_rate != []), 'list is empty'
assert (matches_played != []), 'list is empty'

In [7]:

# closing the driver session

driver.quit()

Generate data frame and csv file

In [8]:

import pandas as pd

In [9]:

# create a dataframe

df = pd.DataFrame({
    "overall_position": overall_position,
    "player_name": player_name,
    "rank": rank,
    "league_points": league_points,
    "win_rate": win_rate,
    "matches_played": matches_played
})

df

Out[9]:

	overall_position	player_name	rank	league_points	win_rate	matches_played
0	5	Nim	Chimpsky	Challenger	954	0%
1	7	Neo	NanChangGodE	Grandmaster	822	0%
2	8	NIKJOJO	1	Grandmaster	802	0%
3	13	noinvade	pls	Grandmaster	658	0%
4	14	Not	Hans	Grandmaster	637	0%
5	17	niewang	zii	Grandmaster	557	0%
6	18	nathanwemiss	u	Grandmaster	552	0%
7	18	NALCS	YI	Grandmaster	552	0%
8	21	NaCl	Tim	Grandmaster	547	0%
9	23	MónkeyD	Luffy	Master	509	0%
10	26	noones	fault	Master	435	0%
11	27	neopets	lover	Master	433	0%
12	31	Notorious	Malli	Master	379	0%
13	34	nodravenday	1	Master	345	0%
14	37	No	Focus	Master	309	0%
15	39	newbury	park	Master	308	0%
16	48	Nice	Bunz	Master	211	0%
17	48	Ninja	Doggy	Master	211	0%
18	61	Not	Viable	Master	93	0%
19	65	Nostalgia	Lee	Master	75	0%
20	66	Never	Story	Master	73	0%
21	68	no1care	me	Master	65	0%
22	72	NIGHTMARE	BABY	Master	45	0%
23	75	Need	Therapy	Master	44	0%
24	75	Niek	Joel	Master	44	0%
25	77	Nickji	18	Master	36	0%
26	82	navel	orange	Master	29	0%
27	82	Mystical	Firefly	Master	29	0%
28	84	NOOB	Fredy41OO	Master	23	0%
29	89	not	skip	Master	18	0%
30	89	MySensei	PzZzang	Master	18	0%
31	94	Not	aIöne	Master	13	0%
32	95	NanoSpeck	v2	Master	2	0%
33	96	NiMama	Boom	Master	1	0%

In [10]:

# create csv file

df.to_csv("na_leaderboard.csv", index=False)

League of legends crawler

primary site for this project: https://tracker.gg/lol

North America Leaderboard

Generate data frame and csv file

Similar Notebooks

Leave a comment Cancel reply