reorganize

1 files changed, 47 insertions, 0 deletions

diff --git a/code/analysisDataset.py b/code/analysisDataset.py
new file mode 100644
index 0000000..34c7a06
--- /dev/null
+++ b/code/analysisDataset.py
@@ -0,0 +1,47 @@
+from parseEml import parseEml
+import os
+
+def read_spf(email_path):
+    mail = parseEml(email_path)
+    auth_result = mail.get_auth_results()
+    if auth_result and "spf=" in auth_result:
+        tmp_list = auth_result.split("spf=")
+        spf_result=tmp_list[1].split(" ")[0]
+    else:
+        spf_result=None
+    return spf_result
+
+#输入：邮件文件夹路径
+#输出：spf认证结果统计dict
+def spf_count(email_folder):
+    spf_count_dict={}
+    files = os.listdir(email_folder)
+    print(email_folder+":\ntotal: "+str(len(files)))
+    for file in files:  # 遍历文件夹
+        if file == "duplicate":
+            continue
+        spf_result=read_spf(email_folder+"/"+file)
+        if spf_result in spf_count_dict:
+            spf_count_dict[spf_result]+=1
+        else:
+            spf_count_dict[spf_result]=1
+    print(spf_count_dict)
+
+#输入：中间域名列表
+#输出：域名出现次数统计结果
+def inter_domain_count(inter_domain_file):
+    count_dict={}
+    with open(inter_domain_file,"r",encoding="utf-8") as f:
+        line = f.readline()
+        while line:
+            line=line.strip()
+            if line in count_dict:
+                count_dict[line]+=1
+            else:
+                count_dict[line]=1
+            line = f.readline()
+        a = sorted(count_dict.items(), key=lambda x: x[1], reverse=True)
+        print(a)
+
+if __name__ == "__main__":
+    inter_domain_count("inter_domain.txt")
\ No newline at end of file