"""Test the wikitablescrape script on four articles."""
import os
import shutil
import wikitablescrape
# Delete previous output folder if it exists, then create a new one
try:
os.remove('TitleID/TitleID.csv')
except:
pass
wikitablescrape.scrape(
url="http://switchbrew.org/index.php?title=Title_list/Games",
output_name="TitleID")
print("done, feel free to exit")
"""Test the wikitablescrape script on four articles."""
import os
import shutil
import wikitablescrape
# Delete previous output folder if it exists, then create a new one
try:
shutil.rmtree('output')
except FileNotFoundError:
pass
wikitablescrape.scrape(
url=
"https://en.wikipedia.org/wiki/List_of_countries_and_dependencies_by_population",
output_name="world_population_by_contry")
wikitablescrape.scrape(
url=
"https://en.wikipedia.org/wiki/List_of_countries_by_carbon_dioxide_emissions",
output_name="carbon_dioxide_by_contry")
# wikitablescrape.scrape(
# url="https://en.wikipedia.org/wiki/List_of_National_Basketball_Association_career_scoring_leaders",
# output_name="nba"
# )
# wikitablescrape.scrape(
# url="https://en.wikipedia.org/wiki/List_of_highest-grossing_films",
# output_name="films"
"""Test the wikitablescrape script on four articles."""
import os
import shutil
import wikitablescrape
# Delete previous output folder if it exists, then create a new one
try:
shutil.rmtree('output')
except FileNotFoundError:
pass
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_current_NBA_team_rosters",
output_name="output"
)
# Move all CSV folders into a single 'output' folder
os.makedirs('output')
shutil.move('./test', './output')
import wikitablescrape
wikitablescrape.scrape(
url=
"https://en.wikipedia.org/wiki/Population_statistics_for_Israeli_settlements_in_the_West_Bank",
output_name="SettlementsPopulation")
# see: https://github.com/rocheio/wiki-table-scrape
"""Test the wikitablescrape script on four articles."""
import os
import shutil
import wikitablescrape
# Delete previous output folder if it exists, then create a new one
try:
shutil.rmtree("output")
except FileNotFoundError:
pass
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_mountains_by_elevation",
output_name="mountains",
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_volcanoes_by_elevation",
output_name="volcanoes",
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_National_Basketball_Association_career_scoring_leaders",
output_name="nba",
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_highest-grossing_films",
output_name="films",
1 record for each zip 3 (roughly 1000 records total)
1 column to record the average temperature for each of 52 weeks, averaged over the last 3 years (52 columns per record)
Temperature values for each record should be in fahrenheit. Whole numbers are sufficient.
"""
import pandas as pd
import wikitablescrape
from wunderground_scraper import scrape_station
import pickle
from datetime import datetime, timedelta
# get a dictionary mapping zip 3 to its address
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_ZIP_code_prefixes",
output_name="zip")
table = pd.read_csv('./zip/zip.csv', header=None)
i = 1
while i < 10:
tmp = pd.read_csv('./zip/zip_{}.csv'.format(i), header=None)
table = table.append(tmp)
i += 1
table = table.replace(['†', '\*'], '', regex=True)
zip_list = []
for j in table.columns:
zip_list += table[j].tolist()
"""Test the wikitablescrape script on four articles."""
import os
import shutil
import wikitablescrape
# Delete previous output folder if it exists, then create a new one
try:
shutil.rmtree('output')
except FileNotFoundError:
pass
wikitablescrape.scrape(
url="https://www.bchydro.com/powersmart/residential/savings-and-rebates/current-rebates-buy-backs/home-renovation-rebates/eligibility.html",
output_name="rebates"
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/R-value_(insulation)",
output_name="insulation"
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_National_Basketball_Association_career_scoring_leaders",
output_name="nba"
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_highest-grossing_films",
output_name="films"
"""Test the wikitablescrape script on four articles."""
import os
import shutil
import wikitablescrape
# Delete previous output folder if it exists, then create a new one
try:
shutil.rmtree('output')
except FileNotFoundError:
pass
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_mountains_by_elevation",
output_name="mountains"
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_volcanoes_by_elevation",
output_name="volcanoes"
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_National_Basketball_Association_career_scoring_leaders",
output_name="nba"
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_highest-grossing_films",
output_name="films"
"""
"""Test the wikitablescrape script on four articles."""
import os
import shutil
import wikitablescrape
# Delete previous output folder if it exists, then create a new one
try:
shutil.rmtree("output")
except FileNotFoundError:
pass
wikitablescrape.scrape(
url=
"https://en.wikipedia.org/wiki/List_of_United_States_cities_by_population",
output_name="cities",
)
wikitablescrape.scrape(
url="https://en.wikipedia.org/wiki/List_of_United_States_cities_by_area",
output_name="areas",
)
# Move all CSV folders into a single 'output' folder
os.makedirs("output")
#shutil.move("./mountains", "./output")
shutil.move("./cities", "./output")
shutil.move("./areas", "./output")