sergiolucero

import requests, pandas as pd
from bs4 import BeautifulSoup
pd.set_option('max_colwidth',-1)

base_url = 'https://www.cntv.cl/cntv/site/tax/port/all/taxport_16___1.html'
bs = BeautifulSoup(requests.get(base_url).text, 'lxml')

top = pd.DataFrame()
links = [link for link in bs.find_all('a') if 'más' in link.text]
print(f'{len(links)} meses de denuncias')

sergiolucero

from math import atan
import folium, pandas as pd

viajes = pd.read_html('http://quant.cl/blc_read')[0]

fm = folium.Map(location=[-33.41,-70.59], zoom_start=14, 
                width=1000, height=400, tiles='stamenwatercolor')

for idx, row in viajes.iterrows():
    fromloc, toloc = eval(row['fromloc']), eval(row['toloc'])      # viene como "string"

sergiolucero

from pptx import Presentation
from pptx.util import Inches
import glob

SLIDE_LAYOUT_TITLE_AND_CONTENT = 1
FILTER = 'fotos/*.jpg'     # what to include

prs = Presentation()
slide_layout = prs.slide_layouts[SLIDE_LAYOUT_TITLE_AND_CONTENT]

sergiolucero

import plotly.graph_objs as go
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
from IPython.display import HTML

trace = go.Sunburst(
    labels=["Carlina", "Alejandro", "Sylvia", "Daniel", "Ingrid", "Juan", "Caty", "Sergio", "Laura", "Miguel"],
    parents=["", "Carlina", "Carlina", "Sylvia", "Sylvia", "Carlina", "Carlina", "Caty", "Carlina", "Carlina"],
    values=[10, 14, 12, 10, 2, 6, 6, 4, 4, 6],
    outsidetextfont = {"size": 20, "color": "#377eb8"},    marker = {"line": {"width": 2}},
)

sergiolucero

import spotipy
import spotipy.util as util
from creds import CLIENT_ID, CLIENT_SECRET

token = util.prompt_for_user_token(username = 'sergiolucero', scope='',
                                   client_id=CLIENT_ID,
                                   client_secret=CLIENT_SECRET,
                                   redirect_uri='http://quant.cl/what'
                                  )

sergiolucero

import requests, pandas as pd
from creds import GOOGLE_KEY

GEO_BASE = 'https://maps.googleapis.com/maps/api/geocode/json?address=%s&key=%s'

def georef(address): #1600+Amphitheatre+Parkway,+Mountain+View,+CA

    url = GEO_BASE %(address, GOOGLE_KEY) 
    res = requests.get(url).json().get('results')   #returns a list
    df = pd.DataFrame(res)

sergiolucero

import pandas as pd
import xml.etree.ElementTree as ET
import requests, sys

def datos(id):
    url = f'https://www.senado.cl/wspublico/tramitacion.php?boletin={id}'
    r=requests.get(url)
    root = ET.fromstring(r.text)
    if len(root):
        pdatos = [root[0][0][ix].text for ix in [2,4,7]]

sergiolucero

import pickle, time
import asyncio
import concurrent.futures
import requests

url_base='https://www.contraloria.cl/opencgrapp/geocgr/api/comunas/%05d/newobras'

def get_comunas(region_id):
    print(f'START {region_id} [{time.ctime()}]')
    region_id = int(region_id)

sergiolucero

import folium
from folium.plugins import MarkerCluster

mc = MarkerCluster()
fm = folium.Map(location=[40.72,-73.98],zoom_start=5)
for _,row in ndf.iterrows():
    mc.add_child(folium.Marker(location=[row['lat'],row['lon']]))
mc.add_to(fm)
fm

sergiolucero

import csv, glob, fitz

def pdf2csv(fn):

    csv_fn = fn.replace('.pdf','.csv')
    region = int(fn[1:3])   # A04101.pdf -> 4

    with open(csv_fn,'w') as fw:
        writer = csv.writer(fw)
        writer.writerow(['nombre','rut','genero','direccion',