def test_remote_download_urls_extract(self):
executor.delete_dir(REMOTE_TARGET, TEST_DATA.creds)
wget.download(REMOTE_TARGET, self.urls, creds=TEST_DATA.creds, extract=True)
act_hash = hasher.get_md5(REMOTE_TARGET, TEST_DATA.creds)
assert act_hash == TEST_DATA.download_md5_extracted, "remote download failed. Expected: {}, Actual: {}".format(
TEST_DATA.download_md5, act_hash
)
def test_local_download_urls_extract(self):
shutil.rmtree(LOCAL_TARGET)
wget.download(LOCAL_TARGET, TEST_DATA.zip_url,\
filenames='x.zip', extract=True)
assert len(glob('{}/*.xml'.format(
LOCAL_TARGET))) > 0, 'Failed to dowload/extract the url.'
shutil.rmtree(LOCAL_TARGET)
def test_local_download_urls(self):
executor.delete_dir(REMOTE_TARGET, TEST_DATA.creds)
wget.download(LOCAL_TARGET, self.urls)
act_hash = hasher.get_md5(LOCAL_TARGET)
assert act_hash == TEST_DATA.download_md5, "local download failed. Expected: {}, Actual: {}".format(
TEST_DATA.download_md5, act_hash
)
def test_remote_download_urls(self):
executor.delete_dir(REMOTE_TARGET, TEST_DATA.creds)
wget.download(REMOTE_TARGET, self.urls, creds=TEST_DATA.creds)
act_hash = hasher.get_md5(REMOTE_TARGET, TEST_DATA.creds)
assert act_hash==TEST_DATA.download_md5,\
'remote download failed. Expected: {}, Actual: {}'\
.format(TEST_DATA.download_md5, act_hash)
def test_download_with_key(self):
executor.delete_dir(REMOTE_TARGET, TEST_DATA.creds)
wget.download(REMOTE_TARGET, self.urls, creds=TEST_DATA.creds)
rsync.download(REMOTE_TARGET, LOCAL_TARGET, creds=TEST_DATA.creds)
act_hash = hasher.get_md5(REMOTE_TARGET, TEST_DATA.creds)
assert act_hash == TEST_DATA.download_md5, "upload failed. Expected: {}, Actual: {}".format(
TEST_DATA.download_md5, act_hash
)
def test_download_with_key(self):
executor.delete_dir(REMOTE_TARGET, TEST_DATA.creds)
wget.download(REMOTE_TARGET, self.urls, creds=TEST_DATA.creds)
rsync.download(REMOTE_TARGET, LOCAL_TARGET, creds=TEST_DATA.creds)
act_hash = hasher.get_md5(REMOTE_TARGET, TEST_DATA.creds)
assert act_hash==TEST_DATA.download_md5,\
'upload failed. Expected: {}, Actual: {}'\
.format(TEST_DATA.download_md5, act_hash)
def main(lon, lat):
'''First argument degrees longitude (E is positive, W negative)
of the landslide location,
second argument latitude (N positive, S negative),
in decimal format(not minutes etc.)'''
nlat, wlon, slat, elon = ten_km_square(lat, lon)
#print("(NLat:{:.4f},WLon:{:.4f}),(SLat:{:.4f},ELon:{:.4f});".format(nlat, wlon, slat, elon))
region = (
'[{:.4f},{:.4f}], [{:.4f},{:.4f}], [{:.4f},{:.4f}], [{:.4f},{:.4f}]'.
format(wlon, nlat, elon, nlat, wlon, slat, elon, slat))
rectangle = ('[{:.4f},{:.4f},{:.4f},{:.4f}]'.format(
wlon, slat, elon, nlat))
lister = region.split('/')
finallist = [ast.literal_eval(i) for i in lister] # to remove apostrophe
final = [list(value) for value in finallist] # final list
print(final)
import ee
import ee.mapclient
import ee
ee.Initialize()
import ee.mapclient
start = ee.Date('2017-01-01')
finish = ee.Date('2017-03-20')
rectangle = ee.Geometry.Polygon(
final
) #passing the final value as the polygon boundaries defined 10km square area
collection = ee.ImageCollection('COPERNICUS/S2')
filteredCollection = collection.filterBounds(rectangle).filterDate(
start, finish)
first = filteredCollection.first()
path = first.getDownloadURL({'region': final, 'scale': 10})
print(path)
urls = [path]
wget.download(
'/home/path/to/save', urls[0], filenames='x.zip',
extract=True) #path to your location to save a particular image
def get_pdfs(listofurls):
if len(listofurls)<1:
return False
os.mkdir('/tmp/havenpdfs',0755);
numberdownload = 0
try:
items = wget.download('/tmp/havenpdfs', listofurls, extract=False)
numberdownload = numberdownload + 1
except:
print numberdownload
print "Problem..."
return numberdownload
if not(os.path.exists(glove_dir)):
os.makedirs(glove_dir)
with open(osp.join(glove_dir,name ), "wb") as code:
code.write(f.read())
'''
if __name__ == "__main__":
vector_size = [50, 150, 300]
vector_names_glove = [
"glove_wiki_50.txt", "glove_wiki_150.txt", "glove_wiki_300.txt"
]
vector_names_word2vec_50 = ["w2v_wiki_50.txt"]
print "Starting download"
wget.download(glove_dir,
urls=glove_urls,
filenames=vector_names_glove,
parallelism=3)
# print "Downloaded", vector_names_glove
#wget.download(word2vec_dir, urls=w2v_50, filenames=w2v_names_50, parallelism=3)
#print "Downloaded", w2v_names_50
#wget.download(word2vec_dir, urls=w2v_150, filenames=w2v_names_150, parallelism=3)
# print "Downloaded", w2v_names_150
#wget.download(word2vec_dir, urls=w2v_300, filenames=w2v_names_300, parallelism=3)
# print "Downloaded", w2v_names_300
# wget.download(glove_dir, urls=[glove_urls[0]],filenames=[vector_names[0]],parallelism=3)
# wget.download(glove_dir, urls=[glove_urls[1]],filenames=[vector_names[1]],parallelism=3)
# wget.download(glove_dir, urls=[glove_urls[2]],filenames=[vector_names[2]],parallelism=3)
'''
This takes some time. The files are quite big.
def test_local_download_urls_extract(self):
shutil.rmtree(LOCAL_TARGET)
wget.download(LOCAL_TARGET, TEST_DATA.zip_url, filenames="x.zip", extract=True)
assert len(glob("{}/*.xml".format(LOCAL_TARGET))) > 0, "Failed to dowload/extract the url."
shutil.rmtree(LOCAL_TARGET)
mesDrugs = mesResults['drug']
mesEvents = mesDrugs['event']
mesPartitions = mesEvents['partitions']
os.chdir('data')
for partition in mesPartitions:
url = partition['file']
print(url)
file_name = url.split('/')[-1]
dir_name = url.split('/')[-2]
if not os.path.isfile(os.path.join(dir_name, file_name[0:-4])):
if not os.path.isdir(dir_name):
os.makedirs(dir_name)
os.chdir(dir_name)
monfichier = wget.download(os.getcwd(), url, filenames=file_name)
monzip = zipfile.ZipFile(file_name, 'r')
monzip.extractall()
os.remove(file_name)
os.chdir('..')
os.chdir('..')
#I save the fields needed to answer question 1 from the document provided.
#I planned to make use of safetyreportid, safetyreportversion, companynumb, but I did not have time in the end.
#It needs to be done in a more finalised version
#There are several reaction (reactionmeddrapt) fields per record, and we create one separate line for each in the output file
all_files = []
os.chdir('data')
def main3(imgs):
wget.download('.', imgs)
import urllib
import re
from parallel_sync import wget
from os.path import abspath, dirname, join
#
# parse html
#
link = "http://ronnywang-newsdiff.s3-website-ap-northeast-1.amazonaws.com/2016/"
fp = urllib.urlopen(link)
myHTML = fp.read()
matches = re.findall('<a href="201602([^\"]+)">', myHTML, re.DOTALL)
#print(matches)
#
# download
#
prefix = 'http://ronnywang-newsdiff.s3-website-ap-northeast-1.amazonaws.com/2016/201602'
downList = [ prefix + x for x in matches]
#print(downList)
targetPath = join(dirname(abspath(__file__)),'extract')
wget.download(targetPath, downList, extract=True)
for line in status:
orders = int(line)
status.close()
if data['lender'] > orders:
status = open('status.txt', 'w')
status.write(str(data['lender']))
status.close()
media_url = data['path'].split('/')
path = ''
for i in range(media_url.index('media'), len(media_url)):
path = os.path.join(path, media_url[i])
path_details = os.path.join(path, 'details.txt')
mk_dir = os.path.join('/home/flytech/Documents/Projekty/WebMediaRoot', data['name'])
if not os.path.exists(mk_dir):
os.mkdir(mk_dir)
download_target = [os.path.join('http://127.0.0.1:8000/', path_details)]
wget.download(mk_dir, download_target)
details = open(os.path.join(mk_dir, 'details.txt'), 'r')
photos = []
path_photo = os.path.join('http://127.0.0.1:8000/', path)
for line in details:
photos.append(os.path.join(path_photo, line.split(', ')[0]))
wget.download(mk_dir, photos)
time.sleep(1)
def parse_items(self, response):
# Create an item
item = NetCDFScraperItem()
# Populate it
item["url"] = response.url
item["date"] = str(datetime.datetime.utcnow())
item["status"] = "UNKWN"
if response.url.endswith(".nc4") or response.url.endswith(
".nc") or response.url.endswith("dods"):
stored_item = None
# Try to check if this url has been visided using mongodb
client = MongoClient(self.mongodb_url)
user = self.configSectionMap("mongodb")['user']
password = self.configSectionMap("mongodb")['password']
print "user:"******" password:"******"url": response.url})
else:
print "No MongoDb authentication"
client.close()
if stored_item is not None:
# Now a very trivial beahviour
# It should be smarter
item["status"] = "ASTRD"
return item
downloaded = False
tempdir = ""
filename = ""
# Check if it is served by an opendap server
try:
# The netcdf file is hosted by a opendap server
# There is non need to download it
rootgrp = Dataset(response.url)
rootgrp.close()
filename = response.url
except:
# Unfortunatly the netcdf have to be downloaded
tempdir = tempfile._get_default_tempdir() + "/" + next(
tempfile._get_candidate_names())
path = urlparse.urlsplit(response.url).path
filename = tempdir + "/" + posixpath.basename(path)
wget.download(tempdir, response.url)
downloaded = True
# Get the feature
netCDF2JSON = NetCDF2JSON()
feature = netCDF2JSON.get(filename, response.url)
# Remove the downloaed file and directory if needed
if downloaded is True:
os.remove(filename)
os.rmdir(tempdir)
# Check if the feature is valid
if feature is not None:
#print json.dumps(feature,None,"\t")
# Try to save the item in mongodb
client = MongoClient(self.mongodb_url)
if client.netcdf.authenticate(user, password) is True:
db = client.netcdf
items = db.items
item_id = items.insert(feature)
item["status"] = "NEWFT"
else:
print "No MongoDb authentication"
client.close()
# Return the item
return item
def download_urls():
""" downloads some files """
urls = ['http://www.nationalgeographic.com/dc/exposure/homepage/photoconfiguration/image/70759_photo_nxqzsecnr7nwui2pbv33cboxp3vu2hmpyjyavf6lo6pvvsfavj3q_850x478.jpg',\
'http://www.nationalgeographic.com/dc/exposure/homepage/photoconfiguration/image/70867_photo_g2j2wmgshw2nhigkyrhbstxkylvu2hmpyjyavf6lo6pvvsfavj3q_850x478.jpg']
wget.download('/tmp/images', urls, creds=env)
bucket = 'colab-pea'
filename = './10MB'
path = 'test.zip'
#s3.upload_file(filename, bucket, path)
urls = [
'https://newsmaze.net/storage/new_proof_disk/Pea/Director1.7z',
'https://newsmaze.net/storage/new_proof_disk/Pea/Director2.7z',
'https://newsmaze.net/storage/new_proof_disk/Pea/Director3.7z',
'https://newsmaze.net/storage/new_proof_disk/Pea/Director4.7z',
'https://newsmaze.net/storage/new_proof_disk/Pea/Director5.7z',
'https://newsmaze.net/storage/new_proof_disk/Pea/ELGBlockchanin.7z',
'https://newsmaze.net/storage/new_proof_disk/Pea/EnergyProject.7z'
]
# wget.download('/tmp', urls)
# or a single file:
wget.download(os.path.join(os.getcwd(), 'tmp'), urls, tries=10)
for url in urls:
try:
filename = re.search('\w*\.\w*$', url).group(0)
path = os.path.join(os.getcwd(), 'tmp', filename)
#path = f'./tmp/{filename}'
#wget.download(os.path.join(os.getcwd(),'tmp'), url, filenames=filename)
print(f'uploading {filename} to s3')
s3.upload_file(path, bucket, filename)
#os.remove(path)
except:
print(f'error downloading file {url} error: {sys.exc_info()}')
def download_urls():
""" downloads some files """
urls = ['http://www.nationalgeographic.com/dc/exposure/homepage/photoconfiguration/image/70759_photo_nxqzsecnr7nwui2pbv33cboxp3vu2hmpyjyavf6lo6pvvsfavj3q_850x478.jpg',\
'http://www.nationalgeographic.com/dc/exposure/homepage/photoconfiguration/image/70867_photo_g2j2wmgshw2nhigkyrhbstxkylvu2hmpyjyavf6lo6pvvsfavj3q_850x478.jpg']
wget.download('/tmp/images', urls, creds=env)
from parallel_sync import wget import os target_path = os.getcwd() url = "http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2" wget.download(target_path, urls=url)
import urllib
import re
from parallel_sync import wget
from os.path import abspath, dirname, join
#
# parse html
#
link = "http://ronnywang-newsdiff.s3-website-ap-northeast-1.amazonaws.com/2016/"
fp = urllib.urlopen(link)
myHTML = fp.read()
matches = re.findall('<a href="201602([^\"]+)">', myHTML, re.DOTALL)
#print(matches)
#
# download
#
prefix = 'http://ronnywang-newsdiff.s3-website-ap-northeast-1.amazonaws.com/2016/201602'
downList = [prefix + x for x in matches]
#print(downList)
targetPath = join(dirname(abspath(__file__)), 'extract')
wget.download(targetPath, downList, extract=True)
