Skip to content Skip to sidebar Skip to footer

Can't Grab Two Fields From A Webpage In Desired Way

I've created a script in python to fetch two fields (2nd and 3rd columns) time and currency from a table located in a webpage. The script is grabbing the results but not the way I

Solution 1:

Problem is with empty cells in time column

import requests
from bs4 import BeautifulSoup

URL = "https://www.forexfactory.com/calendar.php?week=this"# Make cookie dictionary for setting timezones
cookies={
    "fftimezoneoffset":"0", #timezone / UTC +/-X"fftimeformat":"1", # format 0=am/pm / 1=24hour format"ffdstonoff":"1", # daylight saving"ffverifytimes":"1"# set times to timezone
}
res = requests.get(URL,cookies=cookies) # apply timezones
soup = BeautifulSoup(res.text,"lxml")
lastTime = ""#lastTime for cases with empty values for timesfor item in soup.select("tr.calendar_row"):

    ftime = item.select_one("td.calendar__time").get_text(strip=True)
    iflen(ftime) == 0: #if empty time use last one 
        ftime = lastTime
    lastTime = ftime
    currency = item.select_one("td.calendar__currency").get_text(strip=True)
    iflen(currency) > 0: # print if there is currenty print(ftime,currency)

Solution 2:

You can append data inside an object and store the previous values in case of missing:

import requests
from bs4 import BeautifulSoup

URL = "https://www.forexfactory.com/calendar.php?week=this"

res = requests.get(URL)
soup = BeautifulSoup(res.text,"lxml")

results = []
for item in soup.select("tr.calendar_row"):
    day = item.select_one("td.calendar__date").get_text(strip=True)
    ftime = item.select_one("td.calendar__time").get_text(strip=True)
    currency = item.select_one("td.calendar__currency").get_text(strip=True)
    print(ftime, currency)
    ifnot ftime:
        ftime = previoustime
    ifnot day:
        day = previousday
    if currency:
        results.append(
                {
                'day': day,
                'time': ftime,
                'cur': currency
                }
        )
    previoustime = ftime
    previousday = day

from pprint import pprint
pprint(results)

RESULTS:

[{'cur': 'JPY', 'day': 'SunAug 11', 'time': 'All Day'},
 {'cur': 'CNY', 'day': 'MonAug 12', 'time': '5:00am'},
 {'cur': 'CNY', 'day': 'MonAug 12', 'time': '5:00am'},
 {'cur': 'USD', 'day': 'MonAug 12', 'time': '2:00pm'},
 {'cur': 'NZD', 'day': 'MonAug 12', 'time': '6:45pm'},
 {'cur': 'AUD', 'day': 'MonAug 12', 'time': '6:50pm'},
 {'cur': 'JPY', 'day': 'MonAug 12', 'time': '7:50pm'},
 {'cur': 'AUD', 'day': 'MonAug 12', 'time': '9:30pm'},
 {'cur': 'CNY', 'day': 'MonAug 12', 'time': '10:11pm'},
 {'cur': 'JPY', 'day': 'TueAug 13', 'time': '12:30am'},
 {'cur': 'JPY', 'day': 'TueAug 13', 'time': '1:59am'},
 {'cur': 'EUR', 'day': 'TueAug 13', 'time': '2:00am'},
 {'cur': 'EUR', 'day': 'TueAug 13', 'time': '2:00am'},
 {'cur': 'GBP', 'day': 'TueAug 13', 'time': '4:30am'},
 {'cur': 'GBP', 'day': 'TueAug 13', 'time': '4:30am'},
 {'cur': 'GBP', 'day': 'TueAug 13', 'time': '4:30am'},
 {'cur': 'EUR', 'day': 'TueAug 13', 'time': '5:00am'},
 {'cur': 'EUR', 'day': 'TueAug 13', 'time': '5:00am'},
 {'cur': 'GBP', 'day': 'TueAug 13', 'time': '5:35am'},
 {'cur': 'USD', 'day': 'TueAug 13', 'time': '6:00am'},
 {'cur': 'USD', 'day': 'TueAug 13', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'TueAug 13', 'time': '8:30am'},
 {'cur': 'GBP', 'day': 'TueAug 13', 'time': '9:30am'},
 {'cur': 'JPY', 'day': 'TueAug 13', 'time': '7:50pm'},
 {'cur': 'AUD', 'day': 'TueAug 13', 'time': '8:30pm'},
 {'cur': 'AUD', 'day': 'TueAug 13', 'time': '9:30pm'},
 {'cur': 'CNY', 'day': 'TueAug 13', 'time': '10:00pm'},
 {'cur': 'CNY', 'day': 'TueAug 13', 'time': '10:00pm'},
 {'cur': 'CNY', 'day': 'TueAug 13', 'time': '10:00pm'},
 {'cur': 'CNY', 'day': 'TueAug 13', 'time': '10:00pm'},
 {'cur': 'EUR', 'day': 'WedAug 14', 'time': '2:00am'},
 {'cur': 'EUR', 'day': 'WedAug 14', 'time': '2:45am'},
 {'cur': 'AUD', 'day': 'WedAug 14', 'time': '3:30am'},
 {'cur': 'GBP', 'day': 'WedAug 14', 'time': '4:30am'},
 {'cur': 'GBP', 'day': 'WedAug 14', 'time': '4:30am'},
 {'cur': 'GBP', 'day': 'WedAug 14', 'time': '4:30am'},
 {'cur': 'GBP', 'day': 'WedAug 14', 'time': '4:30am'},
 {'cur': 'GBP', 'day': 'WedAug 14', 'time': '4:30am'},
 {'cur': 'GBP', 'day': 'WedAug 14', 'time': '4:30am'},
 {'cur': 'EUR', 'day': 'WedAug 14', 'time': '5:00am'},
 {'cur': 'EUR', 'day': 'WedAug 14', 'time': '5:00am'},
 {'cur': 'EUR', 'day': 'WedAug 14', 'time': '5:00am'},
 {'cur': 'EUR', 'day': 'WedAug 14', 'time': 'Tentative'},
 {'cur': 'USD', 'day': 'WedAug 14', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'WedAug 14', 'time': '14th-18th'},
 {'cur': 'USD', 'day': 'WedAug 14', 'time': '10:30am'},
 {'cur': 'AUD', 'day': 'WedAug 14', 'time': '7:00pm'},
 {'cur': 'AUD', 'day': 'WedAug 14', 'time': '9:00pm'},
 {'cur': 'AUD', 'day': 'WedAug 14', 'time': '9:30pm'},
 {'cur': 'AUD', 'day': 'WedAug 14', 'time': '9:30pm'},
 {'cur': 'JPY', 'day': 'ThuAug 15', 'time': '12:30am'},
 {'cur': 'EUR', 'day': 'ThuAug 15', 'time': 'All Day'},
 {'cur': 'EUR', 'day': 'ThuAug 15', 'time': 'All Day'},
 {'cur': 'CHF', 'day': 'ThuAug 15', 'time': '2:30am'},
 {'cur': 'GBP', 'day': 'ThuAug 15', 'time': '4:30am'},
 {'cur': 'CAD', 'day': 'ThuAug 15', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '9:15am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '9:15am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '10:00am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '10:00am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '10:30am'},
 {'cur': 'USD', 'day': 'ThuAug 15', 'time': '4:00pm'},
 {'cur': 'NZD', 'day': 'ThuAug 15', 'time': '6:30pm'},
 {'cur': 'EUR', 'day': 'FriAug 16', 'time': '5:00am'},
 {'cur': 'CAD', 'day': 'FriAug 16', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'FriAug 16', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'FriAug 16', 'time': '8:30am'},
 {'cur': 'USD', 'day': 'FriAug 16', 'time': '10:00am'},
 {'cur': 'USD', 'day': 'FriAug 16', 'time': '10:00am'}]

Post a Comment for "Can't Grab Two Fields From A Webpage In Desired Way"