Skip to content

PR-PT-MX-JoseL #21

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.

Sign up for GitHub

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

Open
je-lv wants to merge 1 commit into
base: master
Choose a base branch
from
Open

PR-PT-MX-JoseL #21

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 6 additions & 0 deletions your-code/.ipynb_checkpoints/Untitled-checkpoint.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
{
"cells": [],
"metadata": {},
"nbformat": 4,
"nbformat_minor": 2
}
6 changes: 6 additions & 0 deletions your-code/.ipynb_checkpoints/Untitled1-checkpoint.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
{
"cells": [],
"metadata": {},
"nbformat": 4,
"nbformat_minor": 2
}
219 changes: 219 additions & 0 deletions your-code/.ipynb_checkpoints/liga_mx_data-checkpoint.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,219 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 79,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
" _ _ ___ _____ __ ______ _ \n",
"| | (_) | \\/ |\\ \\ / / | _ \\ | | \n",
"| | _ __ _ __ _| . . | \\ V / | | | |__ _| |_ __ _ \n",
"| | | |/ _` |/ _` | |\\/| | / \\ | | | / _` | __/ _` |\n",
"| |___| | (_| | (_| | | | |/ /^\\ \\ | |/ / (_| | || (_| |\n",
"\\_____/_|\\__, |\\__,_\\_| |_/\\/ \\/ |___/ \\__,_|\\__\\__,_|\n",
" __/ | \n",
" |___/ \n",
" \n"
]
}
],
"source": [
"import base64\n",
"import pandas as pd\n",
"import requests as r\n",
"import ast\n",
"\n",
"print(\"\"\"\n",
" _ _ ___ _____ __ ______ _ \n",
"| | (_) | \\/ |\\ \\ / / | _ \\ | | \n",
"| | _ __ _ __ _| . . | \\ V / | | | |__ _| |_ __ _ \n",
"| | | |/ _` |/ _` | |\\/| | / \\ | | | / _` | __/ _` |\n",
"| |___| | (_| | (_| | | | |/ /^\\ \\ | |/ / (_| | || (_| |\n",
"\\_____/_|\\__, |\\__,_\\_| |_/\\/ \\/ |___/ \\__,_|\\__\\__,_|\n",
" __/ | \n",
" |___/ \n",
" \"\"\")\n",
"\n",
"\n",
"url = \"https://ligamx.net/cancha/estadisticahistorica/1/\"\n",
"base64_string = b'eyJpZERpdmlzaW9uIjoiMSIsImlkVGVtcG9yYWRhIjoiNzAiLCAiaWRUb3JuZW8iOiIxIn0='\n"
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {},
"outputs": [],
"source": [
"header = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'} \n",
"\n",
"decoded = base64.decodebytes(base64_string)\n",
"dec = decoded.decode('UTF-8').replace(\"'\", '\"')\n",
"\n",
"d = ast.literal_eval(dec)\n",
"\n",
"n = int(d['idTemporada']) - 1\n",
"\n",
"l = []"
]
},
{
"cell_type": "code",
"execution_count": 81,
"metadata": {},
"outputs": [],
"source": [
"for i in range(11):\n",
" for x in range(2,0,-1):\n",
" l.append(str({'idDivision': '1', 'idTemporada': str(n), 'idTorneo': str(x)}).replace(' ', '').replace(\"idTorneo\", \" idTorneo\").replace(\"'\", '\"').replace('\",\" ', '\", \"'))\n",
" n-=1\n",
" \n",
"encodedStrings = [str(base64.b64encode(bytes(i, 'utf-8')),'utf-8') for i in l]\n",
"urls = [(url + i) for i in encodedStrings]\n",
"\n",
"dfs_list = []"
]
},
{
"cell_type": "code",
"execution_count": 82,
"metadata": {},
"outputs": [],
"source": [
"def create_dfs(url):\n",
" cont = r.get(url, headers = header).content\n",
" t = pd.read_html(cont, attrs = {'class': 'default tbl_grals'})\n",
" t[0].columns = t[0].columns.droplevel(level=0)\n",
" df = t[0]\n",
" columns=[('General','POS'),('General','Club'),('TOTAL','JJ'),('TOTAL','JG'), ('TOTAL','JE'),('TOTAL','JP'),('TOTAL','GF'),('TOTAL','GC'),('TOTAL','Dif'),('TOTAL','PTS'),\n",
" ('LOCAL','JJ'),('LOCAL','JG'),('LOCAL','JE'),('LOCAL','JP'),('LOCAL','GF'),('LOCAL','GC'),('LOCAL','Dif'),('LOCAL','PTS'),\n",
" ('VISITANTE','JJ'),('VISITANTE','JG'),('VISITANTE','JE'),('VISITANTE','JP'),('VISITANTE','GF'),('VISITANTE','GC'),('VISITANTE','Dif'),('VISITANTE','PTS')]\n",
" df.columns=pd.MultiIndex.from_tuples(columns)\n",
" dfs_list.append(df)\n",
"\n",
"temporada = 2018\n",
"torneo = 2\n",
"\n",
"#URL inicial insertada en input, generar DF inicial\n",
"create_dfs(url + str(base64_string))"
]
},
{
"cell_type": "code",
"execution_count": 83,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[+] Temporada:2018, Torneo:2 --> Appended: ok!\n",
"[+] Temporada:2018, Torneo:1 --> Appended: ok!\n",
"[+] Temporada:2017, Torneo:2 --> Appended: ok!\n",
"[+] Temporada:2017, Torneo:1 --> Appended: ok!\n",
"[+] Temporada:2016, Torneo:2 --> Appended: ok!\n",
"[+] Temporada:2016, Torneo:1 --> Appended: ok!\n",
"[+] Temporada:2015, Torneo:2 --> Appended: ok!\n",
"[+] Temporada:2015, Torneo:1 --> Appended: ok!\n",
"[+] Temporada:2014, Torneo:2 --> Appended: ok!\n",
"[+] Temporada:2014, Torneo:1 --> Appended: ok!\n",
"[+] Temporada:2013, Torneo:2 --> Appended: ok!\n",
"[+] Temporada:2013, Torneo:1 --> Appended: ok!\n",
"[+] Temporada:2012, Torneo:2 --> Appended: ok!\n",
"[+] Temporada:2012, Torneo:1 --> Appended: ok!\n",
"No tables found\n"
]
}
],
"source": [
"try:\n",
" for url in urls:\n",
" create_dfs(url)\n",
" print(f'[+] Temporada:{temporada}, Torneo:{torneo} --> Appended: ok!')\n",
" torneo-=1\n",
" if torneo == 0: \n",
" torneo = 2\n",
" temporada -= 1\n",
"except ValueError as e:\n",
" print(e)\n"
]
},
{
"cell_type": "code",
"execution_count": 84,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[+] Excel Generado!\n"
]
}
],
"source": [
"with pd.ExcelWriter('Estadisticos_LigaMX.xlsx') as writer:\n",
" dfs_list[0].to_excel(writer, sheet_name=f'Temp 2019, Torneo 1')\n",
" for df in dfs_list:\n",
" df.to_excel(writer, sheet_name=f'Temp {temporada}, Torneo {torneo}')\n",
" torneo-=1\n",
" if torneo == 0: \n",
" torneo = 2\n",
" temporada -= 1\n",
"print(\"[+] Excel Generado!\")"
]
},
{
"cell_type": "code",
"execution_count": 86,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['news_test.ipynb',\n",
" 'Estadisticos_LigaMX.xlsx',\n",
" 'Untitled.ipynb',\n",
" '.ipynb_checkpoints',\n",
" 'Untitled1.ipynb']"
]
},
"execution_count": 86,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import os\n",
"\n",
"os.listdir()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Loading