Created
December 18, 2018 15:36
-
-
Save khaerulumam42/dc98552e5eb094b3742fd31654b34172 to your computer and use it in GitHub Desktop.
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
results = {} | |
print("Progress scrapping") | |
for i, code in enumerate(tqdm(list(country_codes.values()))): | |
tmp_data = {} | |
webpage = 'https://www.exchange-rates.org/history/{}/USD/T'.format(code) | |
webpage = requests.get(webpage) | |
webpage = webpage.text | |
soup = BeautifulSoup(webpage, 'html.parser') | |
data = soup.find_all('div', attrs={'class':'table-responsive'}) | |
days = [] | |
currencys = [] | |
dates = [] | |
x = data[0].text[3:-3].split(" ") | |
for i, y in enumerate(x[:-1]): | |
if i % 5 == 0: | |
tmp = [] | |
for i, x in enumerate(list(y.split('/2018')[-1])): | |
if is_number(x) == True: | |
tmp.append(i) | |
days.append((y.split('/2018')[-1])[:tmp[0]]) | |
tmp_curr = (y.split('/2018')[-1])[tmp[0]:tmp[-1]] | |
if ',' in list(tmp_curr): | |
tmp_curr = list(tmp_curr) | |
tmp_curr.remove(',') | |
tmp_curr = "".join(tmp_curr) | |
currencys.append(float(tmp_curr)) | |
tmp_dates = y[:-12].split('2018')[-2].split('/') | |
tmp_dates[-1] = '2018' | |
tmp_dates = "/".join(tmp_dates) | |
dates.append(tmp_dates) | |
if len(days) != len(currencys) and len(days) != len(dates): | |
print("Length days, currencys and days lists must same. got length days {}, currencys {}, dates {}".format(len(days), len(currencys), len(dates))) | |
break | |
else: | |
tmp_data['day'] = days | |
tmp_data['date'] = dates | |
tmp_data['currency'] = currencys | |
results[code] = tmp_data | |
with open('results.json', 'w') as f: | |
json.dump(results, f) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment