replaced assess by logging.warning if number of files

is different from number of expected files

download.py

@@ -19,13 +19,16 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 
-"""Download DARES source data.
+"""Download DARES series from http://dares.travail-emploi.gouv.fr/
 
 Usage:
-  download.py <target_dir>
-  download.py (-h | --help)
+    {self_filename} <target_dir> [options]
+
+Options:
+    --debug                         show debug output
 """
 
+import logging
 import os
 import subprocess
 import sys
@@ -36,13 +39,17 @@ from docopt import docopt
 
 from dares_settings import PROVIDER_URL, SOURCE_FILES_URL, TOP_CATEGORIES
 
+log = logging.getLogger(__name__)
 
 def main():
     args = docopt(__doc__)
     target_dir = os.path.abspath(args['<target_dir>'])
+    debug_mode = args['--debug']
+    logging.basicConfig(format="%(levelname)s: %(message)s", level=(logging.DEBUG if debug_mode else logging.INFO))
 
     for category in TOP_CATEGORIES:
         url = SOURCE_FILES_URL + category["slug"]
+        log.info('* Download {}'.format(url))
         response = requests.get(url)
         response.raise_for_status()
         soup = bs(response.text, "lxml")
@@ -64,10 +71,13 @@ def main():
                 f_url = PROVIDER_URL + a_href
                 f_name = f_url.split("/")[-1]
                 targeted_files.append({"f_name": f_name, "f_url": f_url, "f_title": title})
-        assert len(targeted_files) == category["expected_nb_files"], \
-            (url, len(targeted_files), category["expected_nb_files"])
+        if len(targeted_files) != category["expected_nb_files"]:
+            log.warning("** Number of available files ({}) is different from number of expected files ({})".
+                        format(len(targeted_files), category["expected_nb_files"]))
+
 
-        for targeted_file in targeted_files:
+        for targeted_file in targeted_files[:category["expected_nb_files"]]:
+            log.info('** Download {}'.format(targeted_file["f_url"]))
             response = requests.get(targeted_file["f_url"])
             # f_name = f_url.split("/")[-1] reverting back to url filepath
             filepath = targeted_file["f_name"].split("/")[-1]