summary refs log tree commit diff
diff options
context:
space:
mode:
authorRory& <root@rory.gay>2025-06-05 06:17:31 +0200
committerRory& <root@rory.gay>2025-06-05 06:17:31 +0200
commit54c220f0876102588f462f17faa31e8cfe680d83 (patch)
tree57cd720edde05b864acc7a08de734601094a7d70
parentNormalise property name capitalisation (diff)
downloadBlockScrapersC-54c220f0876102588f462f17faa31e8cfe680d83.tar.xz
Deduplicate patterns, fix dedup.c
-rw-r--r--dedup.c2
-rw-r--r--template/p_user_agent_bot.txt13
2 files changed, 6 insertions, 9 deletions
diff --git a/dedup.c b/dedup.c

index fdfce87..36878c4 100644 --- a/dedup.c +++ b/dedup.c
@@ -104,7 +104,7 @@ char** grow_array(char** array, size_t newSize) void check_dups(char* filename) { printf("# %s:\n", filename); - char** lines = read_lines(PATTERNS_FILE); + char** lines = read_lines(filename); if (lines == NULL) { diff --git a/template/p_user_agent_bot.txt b/template/p_user_agent_bot.txt
index 543adbb..c177145 100644 --- a/template/p_user_agent_bot.txt +++ b/template/p_user_agent_bot.txt
@@ -4,15 +4,12 @@ OAI-SearchBot/ # Claude +claudebot@anthropic.com -ClaudeBot/1.0 +ClaudeBot/ # Facebook -facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php) -facebookexternalhit/1.1 -facebookcatalog/1.0 -meta-externalagent/1.1 (+https://developers.facebook.com/docs/sharing/webmasters/crawler) -meta-externalagent/1.1 -meta-externalfetcher/1.1 (+https://developers.facebook.com/docs/sharing/webmasters/crawler) -meta-externalfetcher/1.1 +facebookexternalhit/ +facebookcatalog/ +meta-externalagent/ +meta-externalfetcher/ # Other (by linked help domain) +http://yandex.com +https://developer.amazon.com