Newer
Older
import requests
import time
import pandas as pd
from datetime import date
from datetime import timedelta
import os.path
import urllib
import tarfile
import shutil
import zipfile
import re
import glob
from selenium import webdriver
from bs4 import BeautifulSoup
from chromedriver_py import binary_path
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support.ui import Select
from selenium.webdriver.support import expected_conditions as EC
def download_data(mode, version, n_max_tries, max_time_per_dl):
baseurl = 'https://www.miteco.gob.es/es/calidad-y-evaluacion-ambiental/temas/atmosfera-y-calidad-del-aire/calidad-del-aire/evaluacion-datos/datos/datos-2001-2021.html'
if mode == 'all':
bdate = date(2001, 1, 1) #date(1960, 1, 1) # date before record starts
edate = date.today()
os.makedirs('/esarchive/obs/ghost/MITECO/original_files/{}/'.format(version), exist_ok=True)
download_location = '/esarchive/obs/ghost/MITECO/original_files/{}/'.format(version)
elif mode == 'nrt':
download_location = '/esarchive/obs/ghost/MITECO/original_files/nrt/'
else:
print('time mode inapplicable')
# create date array; format to YYYYMMDD
years_until_2015 = pd.date_range(bdate, date(2015, 1, 1), freq='Y').strftime('%Y').tolist()
years_after_2015 = pd.date_range(date(2016, 1, 1), edate, freq='Y').strftime('%Y').tolist()
print(years_after_2015)
# set up driver
options = Options()
prefs = {'download.default_directory' : download_location}
options.add_experimental_option('prefs', prefs)
options.add_argument("--no-sandbox")
#options.add_argument("--headless")
svc = webdriver.ChromeService(executable_path=binary_path)
driver = webdriver.Chrome(service=svc, options=options)
# open url
driver.get(baseurl)
# find zip links
html = driver.page_source
soup = BeautifulSoup(html, features="html.parser")
zip_links = soup.find_all("a", href=re.compile(r".zip"))
for zip_link in zip_links:
filename = zip_link.get("href").rpartition('/')[-1]
url = 'https://www.miteco.gob.es/{}'.format(zip_link.get("href"))
while (n_tries < n_max_tries) and (errcode != 200):
r = requests.get(url, timeout=max_time_per_dl)
if r.status_code == 200:
urllib.request.urlretrieve(url, download_location+filename)
print('Downloaded {}'.format(filename))
# unzip
with zipfile.ZipFile(download_location+filename, 'r') as zip_ref:
zip_ref.extractall(download_location)
os.remove(download_location+filename)
errcode = r.status_code
elif r.status_code == 404:
print("No data found, error 404")
errcode = 200
elif r.status_code == 403:
print("Permission denied for {}".format(url))
errcode = 200
else:
# try again
print('Response error {}, attempt {}'.format(r.status_code, n_tries))
errcode = r.status_code
n_tries += 1
max_time_per_dl = max_time_per_dl*2
time.sleep(n_tries ** 2) # wait a lil more every time
if n_tries == n_max_tries:
print('Failed downloading {} {} times in {} seconds, error code {}'.format(url, n_tries, max_time_per_dl, errcode))
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
time.sleep(1)
# go to hyperlinks
for year in years_after_2015:
driver.get('https://www.miteco.gob.es/es/calidad-y-evaluacion-ambiental/temas/atmosfera-y-calidad-del-aire/calidad-del-aire/evaluacion-datos/datos/datos_oficiales_{}.html'.format(year))
if year == '2022':
driver.get('https://www.miteco.gob.es/es/calidad-y-evaluacion-ambiental/temas/atmosfera-y-calidad-del-aire/calidad-del-aire/evaluacion-datos/datos/datos-oficiales-2022.html')
time.sleep(3)
html = driver.page_source
soup = BeautifulSoup(html, features="html.parser")
zip_links = soup.find_all("a", href=re.compile(r".zip"))
for zip_link in zip_links:
filename = zip_link.get("href").rpartition('/')[-1]
#print(filename)
url = 'https://www.miteco.gob.es/{}'.format(zip_link.get("href"))
if year == '2022':
driver.get(url)
time.sleep(5)
# unzip
for zip_file in glob.glob(download_location+'*.zip'):
with zipfile.ZipFile(zip_file, 'r') as zip_ref:
zip_ref.extractall(download_location)
os.remove(zip_file)
continue
while (n_tries < n_max_tries) and (errcode != 200):
r = requests.get(url, timeout=max_time_per_dl)
if r.status_code == 200:
urllib.request.urlretrieve(url, download_location+filename)
print('Downloaded {}'.format(filename))
# unzip
with zipfile.ZipFile(download_location+filename, 'r') as zip_ref:
zip_ref.extractall(download_location)
os.remove(download_location+filename)
errcode = r.status_code
elif r.status_code == 404:
print("No data found, error 404")
errcode = 200
elif r.status_code == 403:
print("Permission denied for {}".format(url))
errcode = 200
else:
# try again
print('Response error {}, attempt {}'.format(r.status_code, n_tries))
errcode = r.status_code
n_tries += 1
max_time_per_dl = max_time_per_dl*2
time.sleep(n_tries ** 2) # wait a lil more every time
if n_tries == n_max_tries:
print('Failed downloading {} {} times in {} seconds, error code {}'.format(url, n_tries, max_time_per_dl, errcode))
time.sleep(1)
# delete metadata
for metadata in glob.glob(download_location+'*.xls'):
os.remove(metadata)
# move files around
alldirectories =[directory for directory in os.listdir(download_location) if not os.path.isfile(os.path.join(download_location, directory))]
for directory in alldirectories:
allfiles = os.listdir(os.path.join(download_location, directory))
for f in allfiles:
os.rename(os.path.join(download_location, directory, f), os.path.join(download_location, f))
try:
shutil.rmtree(os.path.join(download_location, directory))
except:
pass
driver.close()
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
def download_metadata(n_max_tries, max_time_per_dl):
url_metadata = 'https://www.miteco.gob.es/content/dam/miteco/es/calidad-y-evaluacion-ambiental/sgalsi/atm%C3%B3sfera-y-calidad-del-aire/evaluaci%C3%B3n-2022/Metainformacion2022.xlsx'
download_location = "/esarchive/obs/ghost/MITECO/metadata/network_provided/MITECO_META_{}.xlsx"
Headers = {'User-Agent': 'Mozilla/5.0 (iPad; CPU OS 12_2 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148'}
r = requests.get(url_metadata, headers=Headers, timeout=max_time_per_dl)
n_tries = 0
errcode = 999
today = date.today()
while (n_tries < n_max_tries) and (errcode != 200):
if r.status_code == 200:
with open(download_location.format(today.strftime('%Y%m%d')), 'wb') as outfile:
outfile.write(r.content)
print('Downloaded metadata')
errcode = r.status_code
elif r.status_code == 404:
print("No metadata found, error 404")
errcode = 200
else:
# try again
print('Response error {}, attempt {}'.format(r.status_code, n_tries))
errcode = r.status_code
n_tries += 1
time.sleep(n_tries ** 2) # wait a lil more every time
if n_tries == n_max_tries:
print('Failed downloading {} {} times in {} seconds, error code {}'.format(url_metadata, n_tries, max_time_per_dl, errcode))
time.sleep(1)
# convert to csv
file = pd.read_excel(download_location.format(today.strftime('%Y%m%d')))
file.to_csv('/esarchive/obs/ghost/MITECO/metadata/network_provided/MITECO_META_{}.csv'.format(today.strftime('%Y%m%d')), index=False, header=True)
"""# create json from original metadata file
json_metadata = {}
with open('/esarchive/obs/ghost/MITECO/metadata/network_provided/MITECO_META.csv', 'r', encoding='ISO-8859-1') as file:
csv_filedata = csv.DictReader(file)
for row in csv_filedata:
key = row['SiteName_NomDuSite']
update_date = today.strftime('%Y-%m-%d')
for parameter in row:
row[parameter] = {'values': [row[parameter]], 'update_time': [update_date]} # create inner dictionary for every parameter
json_metadata[key] = row
with open('/esarchive/obs/ghost/MITECO/metadata/processed/MITECO_META.json', 'w', encoding='utf-8') as f:
f.write(json.dumps(json_metadata, indent=4))
# create json in desired shape from current metadata file
json_metadata_now = {}
with open(download_location.format(today.strftime('%Y%m%d')), encoding='ISO-8859-1') as file:
csv_filedata = csv.DictReader(file)
for row in csv_filedata:
key = row['SiteName_NomDuSite']
update_date = today.strftime('%Y-%m-%d')
for parameter in row:
row[parameter] = {'values': [row[parameter]], 'update_time': [update_date]} # create inner dictionary for every parameter
json_metadata_now[key] = row
# read standardised file to compare!
with open('/esarchive/obs/ghost/MITECO/metadata/processed/MITECO_META.json', 'r', encoding='ISO-8859-1') as f:
json_metadata = json.loads(f.read())
for station in json_metadata: # loop through all the old stations
if station in json_metadata_now.keys(): # if station is in current meta data, go on
for parameter in json_metadata[station]:
if json_metadata[station][parameter]['values'][-1] != json_metadata_now[station][parameter]['values'][0]: # compare last entry in standardised file to value in new file
# if different value, append the standardised metadeta file
print("old {} --- new {}".format(json_metadata[station][parameter]['values'][-1]), json_metadata_now[station][parameter]['values'][0])
json_metadata[station][parameter]['values'].append(json_metadata_now[station][parameter]['values'][0])
json_metadata[station][parameter]['update_time'].append(json_metadata_now[station][parameter]['update_time'][0])
else:
pass
else:
print('Station {} was abolished'.format(station))
for station in json_metadata_now: # loop through all the new stations
if station in json_metadata.keys(): # if station is in old meta data
pass # comparison was done before
else: # new station appeared!
print('New station {}'.format(station))
json_metadata.update({station: json_metadata_now[station]})
# safe
with open('/esarchive/obs/ghost/MITECO/metadata/processed/MITECO_META.json', 'w', encoding='ISO-8859-1') as f:
f.write(json.dumps(json_metadata, indent=4))"""