Changes on the fetchOrbit.py to download orbit files from the new ESA website (#273)

* Changes to fetchOrbit.py to download orbit files in the new ESA website

I've made changes to the fetchOrbit.py to download the files on the https://scihub.copernicus.eu/gnss/#/home. I've used the generic credentials to query and download the orbit files.

* Update fetchOrbit.py

* Make output path generic

I've used os.path.join on line no. 165 to make it more generic.

* Set the verify option to true

I've set the verify option to True to remove the warning regarding "Unverified HTTPS request".

* Changes to the download link of the fetchOrbit.py

The download link before uses the href link on the XML of the website. It was properly working right until yesterday when it didn't work properly.  

Instead I've edited the script to be consistent instead with the download link on the scihub copernicus GNSS website. I've tested it and it worked properly.

* Update fetchOrbit.py

contrib/stack/topsStack/fetchOrbit.py

@@ -1,22 +1,25 @@
 #!/usr/bin/env python3
 
 import numpy as np
-import re
 import requests
+import re
 import os
 import argparse
 import datetime
 from html.parser import HTMLParser
 
-server = 'http://aux.sentinel1.eo.esa.int/'
+server = 'https://scihub.copernicus.eu/gnss/'
 
-orbitMap = [('precise', 'POEORB/'),
+orbitMap = [('precise', 'AUX_POEORB'),
-            ('restituted', 'RESORB/')]
+            ('restituted', 'AUX_RESORB')]
 
 datefmt = "%Y%m%dT%H%M%S"
 queryfmt = "%Y-%m-%d"
 queryfmt2 = "%Y/%m/%d/"
 
+#Generic credentials to query and download orbit files
+credentials = ('gnssguest', 'gnssguest')
+
 
 def cmdLineParse():
     '''
@@ -55,38 +58,26 @@ def FileToTimeStamp(safename):
 
 class MyHTMLParser(HTMLParser):
 
-    def __init__(self, satName, url):
+    def __init__(self,url):
         HTMLParser.__init__(self)
         self.fileList = []
-        self.in_td = False
-        self.in_a = False
-        self.in_table = False
         self._url = url
-        self.satName = satName
+        
-
     def handle_starttag(self, tag, attrs):
-        if tag == 'td':
+        for name, val in attrs:
-            self.in_td = True
+            if name == 'href':
-        elif tag == 'a':
+                if val.startswith("https://scihub.copernicus.eu/gnss/odata") and val.endswith(")/"):
-            self.in_a = True
+                    pass
-            for name, val in attrs:
+                else:
-                if name == "href":
+                    downloadLink = val.strip()
-                    if val.startswith("http"):
+                    downloadLink = downloadLink.split("/Products('Quicklook')")
-                        self._url = val.strip()
+                    downloadLink = downloadLink[0] + downloadLink[-1]
-
+                    self._url = downloadLink
+                
     def handle_data(self, data):
-        if self.in_td and self.in_a:
+        if data.startswith("S1") and data.endswith(".EOF"):
-            if self.satName in data:
+            self.fileList.append((self._url, data.strip()))
-                self.fileList.append((self._url, data.strip()))
+            
-
-    def handle_tag(self, tag):
-        if tag == 'td':
-            self.in_td = False
-            self.in_a = False
-        elif tag == 'a':
-            self.in_a = False
-            self._url = None
-
 
 def download_file(url, outdir='.', session=None):
     '''
@@ -96,9 +87,9 @@ def download_file(url, outdir='.', session=None):
     if session is None:
         session = requests.session()
 
-    path = os.path.join(outdir, os.path.basename(url))
+    path = outdir
     print('Downloading URL: ', url)
-    request = session.get(url, stream=True, verify=False)
+    request = session.get(url, stream=True, verify=True, auth=credentials)
 
     try:
         val = request.raise_for_status()
@@ -139,37 +130,29 @@ if __name__ == '__main__':
     fileTS, satName, fileTSStart = FileToTimeStamp(inps.input)
     print('Reference time: ', fileTS)
     print('Satellite name: ', satName)
-
     match = None
     session = requests.Session()
 
     for spec in orbitMap:
         oType = spec[0]
-
+        delta = datetime.timedelta(days=1)
-        if oType == 'precise':
+        timebef = (fileTS - delta).strftime(queryfmt)
-            end_date = fileTS + datetime.timedelta(days=20)
+        timeaft = (fileTS + delta).strftime(queryfmt)
-        elif oType == 'restituted':
+        url = server + 'search?q=( beginPosition:[{0}T00:00:00.000Z TO {1}T23:59:59.999Z] AND endPosition:[{0}T00:00:00.000Z TO {1}T23:59:59.999Z] ) AND ( (platformname:Sentinel-1 AND filename:{2}_* AND producttype:{3}))&start=0&rows=100'.format(timebef,timeaft, satName,spec[1])
-            end_date = fileTS
+        
-        else:
-            raise ValueError("Unexpected orbit type: '" + oType + "'")
-        end_date2 = end_date + datetime.timedelta(days=1)
-        urls = (server + spec[1] + end_date.strftime("%Y/%m/%d/") for end_date in (end_date, end_date2))
-
         success = False
         match = None
-
+  
         try:
-            
+            r = session.get(url, verify=True, auth=credentials)
-            for url in urls:
+            r.raise_for_status()
-                r = session.get(url, verify=False)
+            parser = MyHTMLParser(url)
-                r.raise_for_status()
+            parser.feed(r.text)
-                parser = MyHTMLParser(satName, url)
+            for resulturl, result in parser.fileList:
-                parser.feed(r.text)
+                tbef, taft, mission = fileToRange(os.path.basename(result))
-                
+                if (tbef <= fileTSStart) and (taft >= fileTS):
-                for resulturl, result in parser.fileList:
+                    matchFileName = result
-                    tbef, taft, mission = fileToRange(os.path.basename(result))
+                    match = os.path.join(server[0:-5],resulturl[36:])
-                    if (tbef <= fileTSStart) and (taft >= fileTS):
-                        match = os.path.join(resulturl, result)
 
             if match is not None:
                 success = True
@@ -180,8 +163,8 @@ if __name__ == '__main__':
             break
 
     if match is not None:
-
+        output = os.path.join(inps.outdir, matchFileName)
-        res = download_file(match, inps.outdir, session)
+        res = download_file(match, output, session)
         if res is False:
             print('Failed to download URL: ', match)
     else: