-
Notifications
You must be signed in to change notification settings - Fork 0
/
smth_hot_topic.py
166 lines (124 loc) · 4.06 KB
/
smth_hot_topic.py
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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
#!/usr/bin/env python
# coding=utf-8
import requests as rq
import random as rd
from bs4 import BeautifulSoup as bs
from collections import namedtuple
import datetime, time
import sys
import imp
imp.reload(sys)
#sys.setdefaultencoding('utf-8')
Topic = namedtuple('Topic', ['href', 'title', 'published_date', 'num_pages'])
HostName = "http://www.newsmth.net"
def extract_topic(text):
soup = bs(text, features="html.parser")
topic_table = soup.find('table', {'class':'board-list tiz'})
topics = topic_table.findAll('td', {'class':'title_9'})
for elem in topics:
#jump topped topics, eg. <tr class="top"></tr>
if elem.parent.get('class', None) == 'top':
continue
a = elem.find('a')
href = a['href']
title = a.string
num_pages = 1
if (elem.span):
other_pages = elem.span.findAll('a')
num_pages = int(other_pages[-1].text)
published_date = elem.nextSibling.string
try:
timeArray = time.strptime(published_date, "%Y-%m-%d")
except:
today = datetime.date.today()
published_date = today.__str__()
yield Topic(href, title, published_date, num_pages)
def topics_first_n_page(n, board_name):
topics = []
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.107 Safari/537.36',
}
query_dict = {}
url_head = HostName + '/nForum/'
r = rq.get(url_head, params = query_dict)
r.encoding = 'gbk'
url_head = HostName + '/nForum/board/{}?ajax'.format(board_name)
headers = {
'Host': 'www.newsmth.net',
'Connection': 'keep-alive',
'Accept': '*/*',
'X-Requested-With': 'XMLHttpRequest',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.107 Safari/537.36',
'Referer': 'http://www.newsmth.net/nForum/',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'zh-CN,zh;q=0.8'
}
cookies = r.cookies
for page_idx in range(1, n + 1):
query_dict = {'ajax': None, 'p': page_idx}
r = rq.get(url_head, params = query_dict, headers = headers, cookies = cookies)
r.encoding = 'gbk'
topic_generator = extract_topic(r.text)
for topic in topic_generator:
topics.append(topic)
print('Pages scaned: ', page_idx, '/', n)
return topics
def render(render_path, topics):
f = open(render_path, 'w', encoding='utf-8')
def topic_to_tr(topic):
format_tr = '''
<tr>
<td><a href="%s">%s</a></td>
<td>%s</td>
<td>%s</td>
</tr>'''
topic = topic._replace(href = HostName + topic.href)
return format_tr % topic
def topic_tr_itr():
for topic in topics:
topic_tr = topic_to_tr(topic)
yield topic_tr
# for topic_string in topic_tr_itr():
# f.write(topic_string)
table_content = ''.join(topic_tr_itr())
table_templete = '''
<table cellpadding="0" cellspacing="0">
<thead>
<tr>
<th>主题</th>
<th>发帖时间</th>
<th>回复页数</th>
</tr>
</thead>
<tbody>%s</tbody>
</table>'''
table_page = table_templete % table_content
page_templete = '''
<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.0 Transitional//EN'>
<html>
<head>
<meta http-equiv='Content-Type' content='text/html; charset=utf-8'>
<base target = "_blank">
<link rel="stylesheet" type="text/css" href="style.css" >
</head>
<body>
%s
</body>
</html>'''
page = page_templete % table_page
f.write(page)
f.close()
if __name__ == "__main__":
valid_boards = ["WorkLife", "FamilyLife", "RealEstate", "ProgramTrading"]
board_ind = int(input("select a board: {}\n".format({x : valid_boards[x] for x in range(len(valid_boards))})))
pages_cnt = int(input("pages count: "))
pages_cnt = 100 if pages_cnt > 100 else pages_cnt
board_name = valid_boards[board_ind]
topics = topics_first_n_page(pages_cnt, board_name)
# sort by num_pages
topics.sort(key = lambda topic: topic.num_pages, reverse = True)
# delete which num_pages <= 1
topics = filter(lambda topic: topic.num_pages >= 2, topics)
timestamp_str = '{0:%Y%m%d_%H%M%S}'.format(datetime.datetime.now())
render_path = 'SMTH_{}_top{}_{}.html'.format(board_name, pages_cnt, timestamp_str)
render(render_path, topics)