Created
July 3, 2018 20:06
-
-
Save monkeycycle/d7c32077f820ce07004bad5872c7d207 to your computer and use it in GitHub Desktop.
Sunrise Sunset Scraper
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import requests | |
| from bs4 import BeautifulSoup | |
| import csv | |
| from datetime import datetime | |
| file_out = 'sunrise_sunset_toronto.csv' | |
| base_url = 'https://www.timeanddate.com/sun/canada/toronto?month=5&year=2018' | |
| base_city = 'toronto' | |
| base_year = '2017' | |
| root_el_id = 'as-monthsun' | |
| # Open a CSV file for scraping output | |
| f = csv.writer(open(file_out, 'w')) | |
| f.writerow(["date", "month_day", "sunrise", "sunset", "twlight_astro_start", "twlight_astro_end", "twlight_naut_start", "twlight_naut_end", "twlight_civil_start", "twlight_civil_end"]) | |
| # Assemble list of pages to scrape | |
| pages = [] | |
| for i in range(2007, 2017): | |
| base_year = i | |
| for j in range(1, 13): | |
| url = str(base_url) + 'base_city?month=' + str(j) + '&' + str(base_year) | |
| if j < 10: | |
| month = '0' + str(j) | |
| else: | |
| month = str(j) | |
| year = str(base_year) | |
| pages.append([month, year, url]) | |
| for item in pages: | |
| page = requests.get(item[2]) | |
| soup = BeautifulSoup(page.text, 'html.parser') | |
| # Sunrise sunset data is in the #as-monthsun table | |
| table_sun = soup.find("table", {"id": root_el_id}) | |
| table_sun_body = table_sun.find("tbody") | |
| table_sun_rows = table_sun_body.find_all('tr') | |
| for table_sun_row in table_sun_rows: | |
| month_day = table_sun_row.contents[0].text.strip() | |
| month_day = int(month_day) | |
| if month_day < 10: | |
| month_day = '0' + str(month_day) | |
| else: | |
| month_day = str(month_day) | |
| date = str(item[0]) + '-' + str(month_day) + '-' + str(item[1]) | |
| sunrise = table_sun_row.contents[1].text.strip() | |
| sunrise_tmp = sunrise.split(" am ") | |
| sunrise = sunrise_tmp[0] | |
| sunset = table_sun_row.contents[2].text.strip() | |
| sunset_tmp = sunset.split(" pm ") | |
| sunset = sunset_tmp[0] | |
| twlight_astro_start = table_sun_row.contents[5].text.strip() | |
| twlight_astro_end = table_sun_row.contents[6].text.strip() | |
| twlight_naut_start = table_sun_row.contents[7].text.strip() | |
| twlight_naut_end = table_sun_row.contents[8].text.strip() | |
| twlight_civil_start = table_sun_row.contents[9].text.strip() | |
| twlight_civil_end = table_sun_row.contents[10].text.strip() | |
| f.writerow([date, month_day, sunrise, sunset, twlight_astro_start, twlight_astro_end, twlight_naut_start, twlight_naut_end, twlight_civil_start, twlight_civil_end ]) | |
| time.sleep(2) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment