def get_emails(db):
path = "trec06c/dao"
dirs = os.listdir(path)
for dir in dirs:
user = MongoDB.choose_user(db, dir)
emails = os.listdir(path + "/" + dir)
new_emails = []
for e in emails:
email_path = path + "/" + dir + "/" + e
print(email_path)
text = fc.get_text(email_path)
msg = email.message_from_string(text)
title, addresser, addressee, copy = parse_header(msg)
content = parse_body(msg)
content = JB.participle_text(content)
new_email = myEmail.set_email(title, addresser, addressee, copy, content)
new_emails.append(new_email)
# mongodb.insert_many(user, new_emails)
# # 连接邮箱
# host = "imap.qq.com"
# username = "******"
# password = "******"
# title, addresser, addressee, copy, content = get_mail(host, username, password)
# # 中文分词
# content = JB.participle_text(content)
# # 添加至MongoDB数据库
# new_email = myEmail.set_email(title, addresser, addressee, copy, content)
# myClient = mongodb.connect_mongodb()
# emaildb = mongodb.choose_database(myClient)
# user = mongodb.choose_user(emaildb, "demo")
# mongodb.insert_one(user, new_email)
# mongodb.disconnect_mongodb(myClient)
def get_emails(db):
path = "trec06c/data"
dirs = os.listdir(path)
new_emails = []
i = 0
for dir in dirs:
new_emails.clear()
user = MongoDB.choose_user(db, dir)
emails = os.listdir(path + "/" + dir)
j = 0
for e in emails:
print(dir + "/" + e, end=" ")
text = fc.get_text(path + "/" + dir + "/" + e)
print("邮件长度:", len(text))
# 打印某封邮件内容
j = j + 1
msg = email.message_from_string(text)
title, addresser, addressee, copy = pe.parse_header(msg)
date = get_date(text)
print(date)
content = get_content(text)
doc = re.split('。|；|·|！|？|\n', content)
doc = list(filter(None, doc))
split = []
for i in range(len(doc)):
split.append(JB.participle_text(doc[i]))
doc[i] = doc[i] + "。"
# print(split)
emailKind = ""
new_email = myEmail.set_email(title, addresser, addressee, copy,
date, doc, split, emailKind)
new_emails.append(new_email)
i = i + 1
MongoDB.insert_many(user, new_emails)
def keywords_extraction_tt():
file_txt = fc.get_text_2()
keys = jieba.analyse.textrank(file_txt,
topK=20,
withWeight=True,
allowPOS=("ns", "n", "vn", "v"))
for word, weight in keys:
print(word, weight)
def keywords_extraction_tf():
file_txt = fc.get_text_2()
keys = jieba.analyse.extract_tags(file_txt,
topK=20,
withWeight=True,
allowPOS=())
for word, weight in keys:
print(word, weight)
def participle_text(text):
stop_words = fc.get_stop_words()
words = posseg.cut(text) # 默认模式为精准模式，适合文本分析
result = ""
i = 0
for word in words:
if word.word not in stop_words:
if i > 0:
result = result + " " + word.word
else:
result = result + word.word
i = i + 1
return result
def statistics_text_max():
file_txt = fc.get_text()
words = jieba.cut(file_txt)
counts = {}
for word in words:
if len(word) == 1: # 单个单词不考虑
continue
else:
counts[word] = counts.get(word, 0) + 1
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)
for i in range(5):
word, count = items[i]
print("{0:<5}->{1:>5}".format(word, count))