For each group generate also a list of all mangled addresses.

Google Groups (rightly) protects addresses against spammers. There is
(obviously) no way how to find true value of these addresses
programmatically, so we just generate list of all affected ones, which
could be later completed with true values (collected somehow) and fixed
by some other script.

Fixes #275

1 files changed, 27 insertions, 0 deletions

diff --git a/gg_scrapper.py b/gg_scrapper.py
index f1cde21..05eecca 100755
--- a/gg_scrapper.py
+++ b/gg_scrapper.py
@@ -1,5 +1,6 @@
 #!/usr/bin/python3
 
+from configparser import ConfigParser
 import mailbox
 import os.path
 import re
@@ -189,6 +190,29 @@ class Group(Page):
             for art in top.articles:
                 yield art.raw_message
 
+    def collect_mangled_addrs(self):
+        addrs = set()
+        addr_sec_label = 'addresses'
+        for top in self.topics:
+            for art in top.articles:
+                msg_str = art.raw_message
+                # see http://stackoverflow.com/questions/201323
+                msg_matches = re.findall(
+                    r'([a-zA-Z0-9_.+-]+\.\.\.@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+)',
+                    msg_str, re.IGNORECASE)
+                if msg_matches is not None:
+                    for mtch in msg_matches:
+                        addrs.add(mtch)
+
+        addrs = sorted(list(addrs))
+
+        with open('{}.cnf'.format(self.name), 'w') as cnf_f:
+            cnf_p = ConfigParser()
+            cnf_p.add_section(addr_sec_label)
+            for addr in addrs:
+                cnf_p.set(addr_sec_label, addr, '')
+            cnf_p.write(cnf_f)
+
 
 class MBOX(mailbox.mbox):
     def __init__(self, filename):
@@ -219,5 +243,8 @@ def main(group_URL):
     mbx = MBOX("{}.mbx".format(grp.name))
     mbx.write_group(grp)
 
+    # generate list of addresses protected against spammers
+    grp.collect_mangled_addrs()
+
 if __name__ == '__main__':
     main(sys.argv[1])