def get_met_office() -> dict:
"""Get forecast for today"""
raw_html = scrape.simple_get(
'https://www.metoffice.gov.uk/weather/forecast/gcqqnw58n')
soup = BeautifulSoup(raw_html, 'html.parser')
tab_today = soup.find(id="tabDay0")
# the first a is pretty much what we want
a_today = tab_today.find('a')
str_today = str(a_today)
# DRY this up
max_start = str_today.find('Maximum daytime temperature: ') # check for -1
max_finish = str_today.find('C;', max_start) + 1 # check for -1
min_start = str_today.find(
'Minimum nighttime temperature: ') # check for -1
min_finish = str_today.find('C.', min_start) + 1
max_text = str_today[max_start:max_finish]
min_text = str_today[min_start:min_finish]
# text after that and stop at Sunrise
str_sunrise = str_today.find('Sunrise') # check for -1
overview_text = str_today[min_finish + 1:str_sunrise]
return {
'met_min': min_text,
'met_max': max_text,
'met_summary': overview_text,
}
def get_top8_url(event):
# searches for link to top8 decklist page
response = simple_get(event)
soup = BeautifulSoup(response, 'html.parser')
links = []
for link in soup.findAll('a', attrs={'href': re.compile('')}):
links.append(link.get('href'))
top8 = [event for event in links if "top-8-decks" in event]
if len(top8) > 0:
print('https://magic.wizards.com' + top8[0])
return 'https://magic.wizards.com' + top8[0]
else:
return None
def get_bbc() -> dict:
"""Get forecast for today"""
raw_html = scrape.simple_get('https://www.bbc.co.uk/weather/2655708')
soup = BeautifulSoup(raw_html, 'html.parser')
tab_today = soup.find(id="daylink-0")
day_body = tab_today.find('div', class_='wr-day__body')
description = day_body.find(
'div', class_='wr-day__details__weather-type-description').text
min_temp = day_body.find('div', class_='wr-day-temperature__low').text
max_temp = day_body.find('div', class_='wr-day-temperature__high').text
return {
'bbc_min': min_temp,
'bbc_max': max_temp,
'bbc_summary': description,
}
from bs4 import BeautifulSoup
from scrape import simple_get
from requests import post
from adventcode_sessiondata import cookie
import collections
raw_html = simple_get('https://adventofcode.com/2018/day/2/input', cookie)
html = BeautifulSoup(raw_html, 'html.parser')
global stripped_html
stripped_html = html.text.split('\n')
# pop off the last element, which is an empty string
stripped_html.pop()
# stripped_html = ['abcd', 'abdc', 'bbdc', 'ahct', 'thys', 'usyd']
def find_them():
for i in range(len(stripped_html)):
for j in range(i + 1, len(stripped_html)):
count = 0
for k in range(len(stripped_html[1])):
if stripped_html[i][k] != stripped_html[j][k]:
count += 1
if count > 1:
break
else:
pass
if k == 25 and count <= 1:
#'/name/nm0000136/'] # Johnny Depp
#'/name/nm0000152/', # Richard Gere
#'/name/nm0001557/'] # Viggo Mortesen
#'/name/nm0000093/', # Brad Pitt
#'/name/nm0000115/', # Nicolas Cage
#'/name/nm0000018/', # Kirk Douglas
#'/name/nm0000142/', # Clint Eastwood
#'/name/nm0000886/'] # Warren Beaty
# Robert Redford? For comedy?
]
# Update target gender
sc.target_gender = sc.TargetGender('m')
for a in act:
raw_html = sc.simple_get(glob_url + a)
actor_name = get_actor_name(raw_html)
final = trim_movie_list(related_movies(raw_html))
print(str(len(final)) + ' items')
print("Working on actor: " + actor_name)
sc.scrape_movies(final, (actor_name, 'm'))
fact = [ #'/name/nm0000098/' # Jennifer Aniston
'/name/nm0000402/' # Carrie Fisher
'/name/nm0000235/' # Uma Thurman
]
sc.target_gender = sc.TargetGender('f')
for f in fact: