Python中怎么提取邮件内容

基础信息准备

import imaplib, email,re,requests,time,pymysqlimapserver = 'smtp.office365.com'emailuser = "qa.notice@shangri-la.com"emailpasswd = "test123"
#beta环境禅道地址beta_loginhost="http://zen.beta.com/index.php?m=user&f=login"beta_add_bughost="http://zen.beta.com/index.php?m=bug&f=create&productID=10&branch=0&extra=moduleID=0"
#live环境禅道地址live_loginhost="https://zen.live.com/index.php?m=user&f=login"live_add_bughost="https://zen.live.com/index.php?m=bug&f=create&productID=10&branch=0&extra=moduleID=0"
envs="live" #定义使用的环境

数据库连接信息

#连接数据库相关的信息：beta_dicts={ "HOST" : '10.8.2.3', "PORT" : 3306, "USER": 'zentao', "PASSWORD" : 'test123', "NAME":"zentao"}live_dicts={ "HOST" : '10.7.1.7', "PORT" : 3306, "USER": 'zentao', "PASSWORD" : 'test123', "NAME":"zentao"}

数据库查询

#数据库查询操作def executesql(query,envs): try: if(envs=="beta"): conn = pymysql.connect(beta_dicts['HOST'], beta_dicts['USER'], beta_dicts['PASSWORD'], beta_dicts['NAME'], int(beta_dicts['PORT']),charset='utf8') print(beta_dicts) else: conn = pymysql.connect(live_dicts['HOST'], live_dicts['USER'], live_dicts['PASSWORD'], live_dicts['NAME'], int(live_dicts['PORT']),charset='utf8') print(live_dicts) cursor = conn.cursor() cursor.execute(query) result =cursor.fetchall() print("execute successfully!!!") if(len(result)==0): return 0 else: return result[0][0] except Exception as e: print(e) print("execute failed") finally: cursor.close() conn.close()

建立连接与检索

#建立连接与检索匹配的邮件def search(): print("start to connect") conn = imaplib.IMAP4_SSL(imapserver) conn.login(emailuser, emailpasswd) conn.select('INBOX') # 选择收件箱（默认） print(conn) now = time.localtime() nowt = time.strftime("%d-%b-%Y", now) print(nowt) results , data = conn.search(None,'(FROM "Liang.Wu")','(ON "'+str(nowt)+'")') mailidlist = data[0].split() print(mailidlist) try: for id in mailidlist: print(id) resultss, data = conn.fetch(id, '(RFC822)') # 通过邮件id获取邮件，data是fetch到的邮件具体内容 e = email.message_from_bytes(data[0][1])

解释说明与print

 ''' Header()类： email.header.Header(s=None, charset=None, maxlinelen=None, header_name=None, continuation_ws=' ', errors='strict') 其中参数的含义理解如下： s：标头的值，也就是对应 From、To、Subject 的值；  charset：字符集格式，默认是 ASCII，但是一般指定 UTF-8 格式以兼容更多字符；  header_name:标头名，就是 From、To、Subject、Time 等； ''' subject = email.header.make_header(email.header.decode_header(e['SUBJECT'])) mail_from = email.header.make_header(email.header.decode_header(e['From'])) print("邮件的subject是%s" % subject) print("邮件的发件人是%s" % mail_from) body = str(get_body(e), encoding='ISO-8859-1') # utf-8 gb2312 GB18030解析中文日文英文 print("邮件内容是%s" % body) parse1(body) print("good job") except Exception as e: print("we catch an error!!!",e) finally: print("logout is success") print("the finally of operation!!!") conn.logout()

获取邮件主体信息

#获取邮件主体信息def get_body(msg): if msg.is_multipart ():#Return True if the message's payload is a list of sub-Message objects, otherwise return False. When is_multipart() returns False, the payload should be a string object. return get_body(msg.get_payload(0)) else: '''Return the current payload, which will be a list of Message objects when is_multipart() is True,  or a string when is_multipart() is False. If the payload is a list and you mutate the list object, you modify the message's payload in place.''' return msg.get_payload(None , decode=True)

解析邮件内容并提交禅道

# 解析邮件内容并调用禅道提交（上一篇文章结合来看）def parse1(body): pattern = re.compile('Dear Colleagues,
(.*?)Thanks and Regards,
', re.S) pattern1 = re.compile('black">(.*?)', re.S) pattern2=re.compile(';">\r(.*?);\r<',re.S) lists = re.findall(pattern, body) print("*"*10) lists = str(lists[0]).replace("\n", "").split("
") print(lists) resultlist = [] for i in range(len(lists)): if (len(lists[i]) > 1): resultlist.append(lists[i]) print(resultlist) id = resultlist[1] ids=str(str(resultlist[1]).split(":")[1]).lstrip() Subject = resultlist[2] Subjects="[FeedBack-"+str(str(resultlist[1]).split(":")[1]).lstrip() + "]--"+str(str(resultlist[2]).split(":")[1]) Creator = resultlist[3] Creators = str(str(resultlist[3]).split(":")[1]) Category = resultlist[4] IssueCategory = resultlist[5] if ("Low" in resultlist[6]): Severity = "4" Severity_desc = "Severity: Low (Limited business impact)" if ("Medium" in resultlist[6]): Severity = "3" Severity_desc = "Severity: Medium (Functional but impact operations)" if ("High" in resultlist[6]): Severity = "2" Severity_desc = "Severity: High (Major system outage)" Module = resultlist[7] if('black">' in resultlist[8] and '' in resultlist[8]): Details = str(re.findall(pattern1, resultlist[8])[0]).replace(""", "\"") if(';">\r' in resultlist[8] and ';\r<' in resultlist[8]): Details = str(re.findall(pattern2, resultlist[8])[0]).replace(""", "\"") link = resultlist[9] steps = id + "
" + Subject + "
" + Creator + "
" + Category + "
" + IssueCategory + "
" + Severity_desc + "
" + Module + "
" + Details + "
" + link print(steps.replace("
", "\n")) sql="SELECT * FROM zt_bug WHERE title LIKE \"[FeedBack-"+str(ids)+"%\"" print(sql) if(executesql(sql,envs)>=1): print("there is an record exists!!!") #add_bug(Subjects, Creators, Severity, steps,envs) else: add_bug(Subjects,Creators,Severity,steps,envs)

提交bug至禅道

#提交bug到禅道的方法def add_bug(a,b,c,d,e): #此方法可以与上一遍文章结合在一起提交到禅道 pass