python - 如何获取具有 .eml 附件的邮件正文？

Question

我正在用 Python 开发电子邮件客户端应用程序。

如何使用 Imap 获取具有 .eml 附件的邮件正文？

Answer 1

下面的代码完成了这项工作。您需要 python2.7 来运行以下代码，因为这是在过去编码的。但是，您的问题也来自过去，所以我想这很好。该代码非常简单，因此请看一下。

from email import message_from_file
import os

def file_exists (f):
    return os.path.exists(os.path.join(path, f).replace("\\","/"))

def save_file (fn, cont):
    file = open(os.path.join(path, fn).replace("\\","/"), "wb")
    file.write(cont)
    file.close()

def construct_name (id, fn):
    id = id.split(".")
    id = id[0]+id[1]
    return id+"."+fn

def disqo (s):
    s = s.strip()
    if s.startswith("'") and s.endswith("'"): return s[1:-1]
    if s.startswith('"') and s.endswith('"'): return s[1:-1]
    return s

def disgra (s):
    s = s.strip()
    if s.startswith("<") and s.endswith(">"): return s[1:-1]
    return s

def pullout (m, key):
    Html = ""
    Text = ""
    Files = {}
    Parts = 0
    if not m.is_multipart():
        if m.get_filename():
            fn = m.get_filename()
            cfn = construct_name(key, fn)
            Files[fn] = (cfn, None)
            if file_exists(cfn): return Text, Html, Files, 1
            save_file(cfn, m.get_payload(decode=True))
            return Text, Html, Files, 1
        cp = m.get_content_type()
        if cp=="text/plain": Text += m.get_payload(decode=True)
        elif cp=="text/html": Html += m.get_payload(decode=True)
        else:
            cp = m.get("content-type")
            try: id = disgra(m.get("content-id"))
            except: id = None
            o = cp.find("name=")
            if o==-1: return Text, Html, Files, 1
            ox = cp.find(";", o)
            if ox==-1: ox = None
            o += 5; fn = cp[o:ox]
            fn = disqo(fn)
            cfn = construct_name(key, fn)
            Files[fn] = (cfn, id)
            if file_exists(cfn): return Text, Html, Files, 1
            save_file(cfn, m.get_payload(decode=True))
        return Text, Html, Files, 1
    y = 0
    while 1:
        try:
            pl = m.get_payload(y)
        except: break
        t, h, f, p = pullout(pl, key)
        Text += t; Html += h; Files.update(f); Parts += p
        y += 1
    return Text, Html, Files, Parts

def extract (msgfile, key): 
    m = message_from_file(msgfile)
    From, To, Subject, Date = caption(m)
    Text, Html, Files, Parts = pullout(m, key)
    Text = Text.strip(); Html = Html.strip()
    msg = {"subject": Subject, "from": From, "to": To, "date": Date,
        "text": Text, "html": Html, "parts": Parts}
    if Files: msg["files"] = Files
    return msg

def caption (origin):
    Date = ""
    if origin.has_key("date"): Date = origin["date"].strip()
    From = ""
    if origin.has_key("from"): From = origin["from"].strip()
    To = ""
    if origin.has_key("to"): To = origin["to"].strip()
    Subject = ""
    if origin.has_key("subject"): Subject = origin["subject"].strip()
    return From, To, Subject, Date

if __name__ == "__main__":
    global path

    startdirname = "Email"
    num = 1
    for i in range(10000000):
        if os.path.exists(startdirname + str(num)) == False:
            os.makedirs("Email" + str(num))
            break
        else:
            num += 1


    for i in os.listdir("."):
        if i.endswith(".eml") == True:
            nam = i[:-4]
            path = "./" + startdirname + str(num) + "/" + nam

            os.makedirs("./" + startdirname + str(num) + "/" + nam)

            f = open(i, "rb")
            emailDict = extract(f, f.name)
            f.close()

            textFile = ""

            froms = emailDict["from"]
            tos = emailDict["to"]
            subject = emailDict["subject"]
            parts = emailDict["parts"]
            date = emailDict["date"]
            txt = emailDict["text"]
            html = emailDict["html"]

            files = []
            for i in emailDict["files"]:
                files.append(i)

            textFile += "From: " + froms + "\n"
            textFile += "To: " + tos + "\n"
            textFile += "Subject: " + subject + "\n"
            textFile += "Date: " + date + "\n\n"
            textFile += "Files: " + ", ".join(files) + "\n"
            textFile += "Parts: " + str(parts) + "\n\n"
            textFile += "Text:\n\n" + txt + "\n\n" 
            textFile += "HTML:\n\n" + html


            wf = open("./" + startdirname + str(num) + "/" + nam + "/" + "txt_" + nam + ".txt", "w")
            wf.write(textFile)
            wf.close()