summary |
shortlog |
log |
commit | commitdiff |
tree
raw |
patch |
inline | side by side (from parent 1:
c00b4af)
The script helps retrieving the actual html of a public page on
facebook.com, ignoring the pages which require the CAPTCHA.
This allows to have a local copy of the page to test tweeper on.
--- /dev/null
+#!/bin/sh
+#
+# Facebook requires a CAPTCHA most of the times, so keep fetching the URL as
+# long as needed, until the page is shown with no CAPTCHA.
+
+set -e
+
+USER_AGENT="Mozilla/5.0 (Windows NT 6.1; rv:22.0) Gecko/20130405 Firefox/22.0";
+
+while true;
+do
+ # Force language to en-us to make sure that the string matching works
+ OUTPUT=$(wget -nv --user-agent="$USER_AGENT" --header='Accept-Language: en-us' -O - -- "$1")
+ if echo $OUTPUT | grep -q -v "Security Check Required";
+ then
+ echo "$OUTPUT" > facebook.html
+ break
+ fi
+ sleep 5
+done