Scraping table from website [timeanddate.com]

Question

I want to get the historical hourly weather data from https://www.timeanddate.com/

This is the website link:https://www.timeanddate.com/weather/usa/dayton/historic?month=2&year=2016 - Here I am selecting February and 2016, and the result will appear in the bottom of the page.

I used the following steps:https://stackoverflow.com/a/47280970/9341589

and it is working perfectly on the "first day of each month", I want to parse all the month, and if it is possible all the year.

below the code I am using (to parse March 1, 2016):

from urllib.request import urlopen
from bs4 import BeautifulSoup
url = "https://www.timeanddate.com/weather/usa/dayton/historic?month=3&year=2016"
page = urlopen(url)
soup = BeautifulSoup(page, "html.parser")

Data = []
table = soup.find('table', attrs={'id':'wt-his'})
for tr in table.find('tbody').find_all('tr'):
   dict = {}
   dict['time'] = tr.find('th').text.strip()
   all_td = tr.find_all('td')
   dict['temp'] = all_td[1].text
   dict['weather'] = all_td[2].text
   dict['wind'] = all_td[3].text
   arrow = all_td[4].text


   dict['humidity'] = all_td[5].text
   dict['barometer'] = all_td[6].text
   dict['visibility'] = all_td[7].text

   Data.append(dict)

this is the result for March 1:

This is because the website "url", the link only include the month and year, and to change the days, for instance, from Feb1 to Feb 3, the tab is shown in the pic attached needed to be used:

Answer 1

You can iterate over the table elements (tr, th, and td) for a single page:

import requests, re, typing
from bs4 import BeautifulSoup as soup
import contextlib
def _remove(d:list) -> list:
   return list(filter(None, [re.sub('\xa0', '', b) for b in d]))

@contextlib.contextmanager
def get_weather_data(url:str, by_url = True) -> typing.Generator[dict, None, None]:
   d = soup(requests.get(url).text if by_url else url, 'html.parser')
   _table = d.find('table', {'id':'wt-his'})
   _data = [[[i.text for i in c.find_all('th')], *[i.text for i in c.find_all('td')]] for c in _table.find_all('tr')]
   [h1], [h2], *data, _ = _data
   _h2 = _remove(h2)
   yield {tuple(_remove(h1)):[dict(zip(_h2, _remove([a, *i]))) for [[a], *i] in data]}


with get_weather_data('https://www.timeanddate.com/weather/usa/dayton/historic?month=2&year=2016') as weather:
 print(weather)

Output:

{('Conditions', 'Comfort'): [{'Time': '12:58 amMon, Feb 1', 'Temp': '50°F', 'Weather': 'Light rain. Mostly cloudy.', 'Wind': '13 mph', 'Humidity': '↑', 'Barometer': '88%', 'Visibility': '29.79 "Hg'}, {'Time': '1:58 am', 'Temp': '46°F', 'Weather': 'Mostly cloudy.', 'Wind': '12 mph', 'Humidity': '↑', 'Barometer': '83%', 'Visibility': '29.82 "Hg'}, {'Time': '2:58 am', 'Temp': '43°F', 'Weather': 'Mostly cloudy.', 'Wind': '14 mph', 'Humidity': '↑', 'Barometer': '85%', 'Visibility': '29.87 "Hg'}, {'Time': '3:58 am', 'Temp': '42°F', 'Weather': 'Mostly cloudy.', 'Wind': '10 mph', 'Humidity': '↑', 'Barometer': '83%', 'Visibility': '29.89 "Hg'}, {'Time': '4:58 am', 'Temp': '41°F', 'Weather': 'Mostly cloudy.', 'Wind': '10 mph', 'Humidity': '↑', 'Barometer': '82%', 'Visibility': '29.91 "Hg'}, {'Time': '5:58 am', 'Temp': '39°F', 'Weather': 'Mostly cloudy.', 'Wind': '8 mph', 'Humidity': '↑', 'Barometer': '83%', 'Visibility': '29.93 "Hg'}, {'Time': '6:58 am', 'Temp': '38°F', 'Weather': 'Partly cloudy.', 'Wind': '5 mph', 'Humidity': '↑', 'Barometer': '82%', 'Visibility': '29.96 "Hg'}, {'Time': '7:58 am', 'Temp': '38°F', 'Weather': 'Partly sunny.', 'Wind': '5 mph', 'Humidity': '↑', 'Barometer': '80%', 'Visibility': '29.99 "Hg'}, {'Time': '8:58 am', 'Temp': '38°F', 'Weather': 'Overcast.', 'Wind': '5 mph', 'Humidity': '↑', 'Barometer': '78%', 'Visibility': '30.01 "Hg'}, {'Time': '9:58 am', 'Temp': '40°F', 'Weather': 'Broken clouds.', 'Wind': '7 mph', 'Humidity': '↑', 'Barometer': 'N/A', 'Visibility': '30.01 "Hg'}, {'Time': '10:58 am', 'Temp': '41°F', 'Weather': 'Broken clouds.', 'Wind': '1 mph', 'Humidity': '↑', 'Barometer': '72%', 'Visibility': '30.02 "Hg'}, {'Time': '11:58 am', 'Temp': '41°F', 'Weather': 'Partly sunny.', 'Wind': '2 mph', 'Humidity': '↑', 'Barometer': '70%', 'Visibility': '30.04 "Hg'}, {'Time': '12:58 pm', 'Temp': '42°F', 'Weather': 'Scattered clouds.', 'Wind': '2 mph', 'Humidity': '↑', 'Barometer': '69%', 'Visibility': '30.04 "Hg'}, {'Time': '1:58 pm', 'Temp': '43°F', 'Weather': 'Partly sunny.', 'Wind': '3 mph', 'Humidity': '↑', 'Barometer': '65%', 'Visibility': '30.03 "Hg'}, {'Time': '2:58 pm', 'Temp': '44°F', 'Weather': 'Partly sunny.', 'Wind': 'No wind', 'Humidity': '↑', 'Barometer': '62%', 'Visibility': '30.02 "Hg'}, {'Time': '3:58 pm', 'Temp': '46°F', 'Weather': 'Passing clouds.', 'Wind': '6 mph', 'Humidity': '↑', 'Barometer': '58%', 'Visibility': '30.03 "Hg'}, {'Time': '4:58 pm', 'Temp': '46°F', 'Weather': 'Sunny.', 'Wind': '6 mph', 'Humidity': '↑', 'Barometer': '57%', 'Visibility': '30.04 "Hg'}, {'Time': '5:58 pm', 'Temp': '43°F', 'Weather': 'Clear.', 'Wind': '3 mph', 'Humidity': '↑', 'Barometer': '65%', 'Visibility': '30.06 "Hg'}, {'Time': '6:58 pm', 'Temp': '39°F', 'Weather': 'Clear.', 'Wind': '1 mph', 'Humidity': '↑', 'Barometer': '71%', 'Visibility': '30.09 "Hg'}, {'Time': '7:58 pm', 'Temp': '35°F', 'Weather': 'Clear.', 'Wind': '1 mph', 'Humidity': '↑', 'Barometer': '79%', 'Visibility': '30.11 "Hg'}, {'Time': '8:58 pm', 'Temp': '32°F', 'Weather': 'Clear.', 'Wind': 'No wind', 'Humidity': '↑', 'Barometer': '85%', 'Visibility': '30.13 "Hg'}, {'Time': '9:58 pm', 'Temp': '30°F', 'Weather': 'Clear.', 'Wind': 'No wind', 'Humidity': '↑', 'Barometer': '91%', 'Visibility': '30.14 "Hg'}, {'Time': '10:58 pm', 'Temp': '28°F', 'Weather': 'Clear.', 'Wind': '5 mph', 'Humidity': '↑', 'Barometer': '93%', 'Visibility': '30.14 "Hg'}, {'Time': '11:58 pm', 'Temp': '29°F', 'Weather': 'Clear.', 'Wind': 'No wind', 'Humidity': '↑', 'Barometer': '90%', 'Visibility': '30.13 "Hg'}]}

However, in order to scrape the data for all days in the desired month, selenium must be used, as the site dynamically updates the DOM via a request to the backend:

from selenium import webdriver
d = webdriver.Chrome('/Path/to/chromedriver')
d.get('https://www.timeanddate.com/weather/usa/dayton/historic?month=2&year=2016')
_d = {}
for i in d.find_element_by_id('wt-his-select').find_elements_by_tag_name('option'):
  i.click()
  with get_weather_data(d.page_source, False) as weather:
    _d[i.text] = weather

Edit: to iterate over the full data results, use dict.items:

for a, b in _d.items():
  pass #do something with a and b