From 4075a58165011308febe6aa85873c5de751417e9 Mon Sep 17 00:00:00 2001 From: Xavier Claude Date: Wed, 3 Aug 2016 15:52:28 +0200 Subject: [PATCH] Write the alexa top1M zip file after download --- tools/generate-alexa.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/generate-alexa.py b/tools/generate-alexa.py index 012b62b..46c5fca 100644 --- a/tools/generate-alexa.py +++ b/tools/generate-alexa.py @@ -10,6 +10,9 @@ alexa_url = "http://s3.amazonaws.com/alexa-static/top-1m.csv.zip" alexa_file = "top-1m.csv.zip" user_agent = {"User-agent":"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0"} r = requests.get(alexa_url, headers=user_agent) +with open(alexa_file, 'wb') as fd: + for chunk in r.iter_content(4096): + fd.write(chunk) with zipfile.ZipFile(alexa_file, 'r') as alexa_lists: for name in alexa_lists.namelist(): if name == "top-1m.csv":