【PYTHON】urllib basics

 # urllib basics

from urllib.request import urlopen

url = 'https://en.wikipedia.org/wiki/General-purpose_programming_language'

page = urlopen(url).read()

page[:50]

page[:50].decode('utf-8')

page[-100:]

from bs4 import UnicodeDammit

suggestion = UnicodeDammit(page)

suggestion.original_encoding

datafile_url = 'https://docs.misoenergy.org/marketreports/20210203_mom.xlsx'

mom_data = urlopen(datafile_url).read()

mom_data[:20]

import pandas as pd

df = pd.read_excel(mom_data)

df.head()

df = pd.read_excel(datafile_url)

df.head()

df.to_excel('mom_report.xlsx')

with open('mom_report.xlsx', 'wb') as f:

    f.write(mom_data)

from urllib.request import urlretrieve

urlretrieve(datafile_url, 'mom_report.xlsx')

df = pd.read_excel('mom_report.xlsx')

df.head()