1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
|
import sys
import MySQLdb
from datetime import *
filepath = sys.argv[1]
array = filepath.split("/")
category = array[1]
filename = array[3]
print "filepath: " + filepath
dict = {'id': '', 'name': filename, 'category': category, 'tag': '', 'title': '', 'img': '',
'intro': '', 'tag_id': '', 'tag_name': '', 'body': ''}
def getIntro(line, bodyDict, markDict):
for k in markDict:
if markDict[k] < 2:
se = "<" + k + ">"
ee = "</" + k + ">"
if line.find(se) >= 0:
if line.find(ee) > 0:
bodyDict[k] = line[len(se):(len(line) - len(ee) - 1)]
markDict[k] = 2
else:
bodyDict[k] = bodyDict[k] + line[len(se):len(line)]
markDict[k] = 1
elif line.find(ee) >= 0:
bodyDict[k] = bodyDict[k] + line[0:(len(line) - len(ee) - 1)]
markDict[k] = 2
else:
if markDict[k] == 1:
bodyDict[k] = bodyDict[k] + line
markDict[k] = 1
def parse_html():
file_html = open("/opt/apps/nginx-apps/blog/" + filepath)
body = ''
flag_body = False
flag_note = False
markDict = {"id": 0, "tag": 0, "title": 0, "img": 0, "intro": 0}
for line in file_html.xreadlines():
if line.find("<body>") >= 0:
flag_body = True
elif flag_body:
if line.find("<!--intro") >= 0:
flag_note = True
elif line.find("intro-->") >= 0:
flag_note = False
if flag_note:
getIntro(line, dict, markDict)
body = body + line
dict['body'] = body
return dict
def update_data(dict):
conn = MySQLdb.connect(host='127.0.0.1', user='mysql_blog', passwd='mysqBlogPWD2016', db='blog', charset='utf8')
cur = conn.cursor()
try:
tag_id = []
tag_arr = dict['tag'].split(",")
for tag in tag_arr:
tag = tag.strip()
sql = "SELECT id FROM t_tag WHERE lower(tag) = %s"
print sql
cur.execute(sql, (tag.lower(),))
results = cur.fetchone()
if not results:
sql = "INSERT INTO t_tag(tag, type, status) VALUES(%s, %s, %s)"
print sql
cur.execute(sql, (tag, "2", "1"))
ido = conn.insert_id()
ids = str(ido)
tag_id.append(ids)
else:
tag_id.append(str(results[0]))
sql = "SELECT COUNT(1) FROM t_article WHERE id = %s"
print sql
cur.execute(sql, (int(dict['id']),))
results = cur.fetchone()
now_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
tag_ids = ",".join(tag_id)
intro = dict['intro'].replace('\n', '').replace('\r', '')
if results[0] <= 0:
sql = "INSERT INTO t_article(id, title, content, html, tag_id, tag_name, img_path, " \
"status, create_time) VALUES(%s, %s, %s, %s, %s, %s, %s, %s, %s)"
print sql
cur.execute(sql, (int(dict['id']), dict['title'], intro, dict['body'], tag_ids, dict['tag'],
dict['img'], '1', now_time))
cur.execute(create_sql(tag_id, int(dict['id'])))
else:
sql = "UPDATE t_article SET title=%s, content=%s, html=%s, tag_id=%s, tag_name=%s, " \
"img_path=%s, update_time=%s WHERE id = %s"
print sql
cur.execute(sql, (dict['title'], intro, dict['body'], tag_ids, dict['tag'],
dict['img'], now_time, int(dict['id'])))
sql = "DELETE FROM t_article_tag WHERE aid = %s"
print sql
cur.execute(sql, (int(dict['id']),))
cur.execute(create_sql(tag_id, int(dict['id'])))
conn.commit()
except Exception, e:
raise e
finally:
cur.close()
conn.close()
def create_sql(tag_id, aid):
sql = "INSERT INTO t_article_tag(aid, tagid) VALUES"
values = []
for tag in tag_id:
values.append('(' + str(aid) + ',' + str(tag) + ')')
sql = sql + ",".join(values)
print sql
return sql
data = parse_html()
update_data(data)
|
