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
| # -*- coding=utf-8 -*-
import sys
reload(sys)
sys.setdefaultencoding( "utf-8" )
import urllib2
import MySQLdb
import time
from bs4 import BeautifulSoup
import smtplib
from email.mime.text import MIMEText
from email.header import Header
def download(url):
try:
html = urllib2.urlopen(url).read()
except urllib2.URLError as e:
print "error"
print e.code # 可以打印出来错误代号如404。
print e.reason # 可以捕获异常
html = None
return html
def email(text ,toemail):
sender = "rain@rain1024.com" #发送方的邮箱
password = "" #邮箱的授权码
receiver = toemail #接收方的邮箱
data_time = time.strftime("%Y-%m-%d")
subject = data_time + "的CSDN博客报告" #title邮件标题
words = text #text邮件内容
smtpserver = 'smtp.exmail.qq.com'
msg = MIMEText(words, 'plain', 'utf-8')#中文需参数‘utf-8'，单字节字符不需要
msg['Subject'] = Header(subject, 'utf-8') #邮件标题
msg['from'] = sender #发信人地址
msg['to'] = receiver #收信人地址
smtp = smtplib.SMTP_SSL("smtp.exmail.qq.com", 465)
smtp.connect('smtp.exmail.qq.com')
smtp.login(sender, password)
smtp.sendmail(sender, receiver, msg.as_string())
smtp.quit()
print data_time + "的邮件发送成功!"
def operator_SQL(flag,update=None):
# 将获取的数据存入数据库中
try:
conn = MySQLdb.connect(
host='127.0.0.1',
port=3306,
user='root',
passwd='root',
db='test',
charset='utf8',
)
except:
conn = MySQLdb.connect(
host='127.0.0.1',
port=3306,
user='test',
passwd='',
db='test',
charset='utf8',
)
cur = conn.cursor()
if flag == 1:
res = cur.execute("select * from csdn_article")
cur.execute(
'insert into csdn_article values("%s","%s", "%s", "%s", "%s")' % (res + 1, update[0], update[1], update[2], 0))
elif flag == 2:
cur.execute("update csdn_article set article_read="+str(update[1])+" where article_id = "+str(update[0]))
cur.execute("update csdn_article set change_read=" + str(
update[3]) + " where article_id = " + str(update[0]))
elif flag == 3:
res = cur.execute("select article_read from csdn_article where article_id="+str(update))
if res == 1:
res = cur.fetchmany(res)[0][0]
elif res == 0:
res = -1
return res
# sql_list = list(cur.fetchmany(res))
# print sql_list[1].count(435)
# if 435 in sql_list:
# print '432432443242'
cur.close()
conn.commit()
conn.close()
def extract(html):
soup = BeautifulSoup(html)
# 获取到评论等内容
comment = soup.find(attrs={'id':'blog_statistics'}).text
# 接下来获取每一篇文章的阅读数，与数据库中的数据进行判断，如果有变化，则记录下来
article_soup = soup.find_all(attrs={'class':'list_item article_item'})
article_all_list = []
for value in article_soup:
# 根据每篇文章的特征提取对应的数据
value = str(value)
tmp_soup = BeautifulSoup(value)
article_id = tmp_soup.a['href']
article_title = tmp_soup.find('span',class_='link_title').contents[0].string
article_read = tmp_soup.find('span',class_='link_view').contents[1].string
# print article_id,article_read,article_title
# 使用了各种办法，终于将两个字符串中的数字提取出来了
article_id = int(str.split(str(article_id),'/')[4])
article_read = int(str.split(str(article_read[1:]),')')[0])
# 然后将每一篇文章里的数据放入一个列表里，再将这个列表放到大的列表里
article_list = []
article_list.append(article_id)
article_list.append(article_read)
article_list.append(article_title)
# 对每个值去数据库里查找，如果存在就进行比较，不相同则记录下来，并去数据库中修改，如果不存在，则插入这条数据
read = operator_SQL(3, article_id)
if read == -1:
operator_SQL(1, article_list)
elif read != article_read:
# 将阅读次数的查值传入数据库中
article_list.append(article_read - read)
# print article_list[3]
operator_SQL(2, article_list)
article_all_list.append(article_list)
text = "您今天的CSDN博客信息报告如下："
text = text + str(comment)
text = text + '今日有' + str(article_all_list.__len__()) + '篇文章的阅读数发生了变化' + '\n'
i = 1
for value in article_all_list:
# print value[0]
text = text + str(i) + '： ' + value[2] + '总阅读次数为：'+ str(value[1]) + '；比昨天增加了：' + str(value[3]) + '次。' + '\n'
i = i + 1
# print text
return text
def main():
url = 'http://blog.csdn.net/rain_web/article/list/500'
html = download(url)
text = extract(html=html)
email(text,'nylrain@163.com')
# operator_SQL(3, 353425)
if __name__=='__main__':
main()
|
