From 4732bbbbd4d14a45d166781fde435e8b509e5a3e Mon Sep 17 00:00:00 2001
From: rusinthread <rusinthread@cock.li>
Date: Fri, 6 Jan 2017 19:56:51 +0300
Subject: test data.md generation

---
 find_2ch_archive.py | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

(limited to 'find_2ch_archive.py')

diff --git a/find_2ch_archive.py b/find_2ch_archive.py
index 0358307..2ddb211 100755
--- a/find_2ch_archive.py
+++ b/find_2ch_archive.py
@@ -1,6 +1,6 @@
 #!/usr/bin/python3
 import requests, re
-import sys
+#import sys
 
 def test_link_text(text):
     text = text.upper()
@@ -31,15 +31,19 @@ def test_link_text(text):
 def full_url(url):
     return 'https://2ch.hk' + url
 
-page = 500
-board = "b"
-while page <= 600:
-    print("fetching page %d" % page)
-    url = "https://2ch.hk/%s/arch/%d.html" % (board, page)
-    r = requests.get(url)
-    for a in re.finditer(r'<a href="(/'+board+'/arch/[\d-]+/res/\d+\.html)">(.*?)</a>', r.text, flags=re.I|re.M):
-        link_href = a.group(1)
-        link_text = a.group(2)
-        if test_link_text(link_text):
-            print("[%d] %s => %s" % (page, full_url(link_href), link_text))
-    page += 1
+def find_triumfalno():
+    page = 500
+    board = "b"
+    while page <= 600:
+        #print("fetching page %d" % page)
+        url = "https://2ch.hk/%s/arch/%d.html" % (board, page)
+        r = requests.get(url)
+        for a in re.finditer(r'<a href="(/'+board+'/arch/[\d-]+/res/\d+\.html)">(.*?)</a>', r.text, flags=re.I|re.M):
+            link_href = a.group(1)
+            link_text = a.group(2)
+            if test_link_text(link_text):
+                print("%s => %s" % (full_url(link_href), link_text))
+        page += 1
+
+if __name__ == '__main__':
+    find_triumfalno()
-- 
cgit v1.2.3