Machine_Personality/hupuexample.py at master · squarelimber/Machine_Personality · GitHub

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
from bs4 import BeautifulSoup
import chardet
import requests
import pprint
import json
import pandas as pd
import numpy as np

'''
creat beautifulsoup
'''
def creat_bs(url):
    result = requests.get(url)
    e=chardet.detect(result.content)['encoding']
    #set the code of request object to the webpage's code
    result.encoding=e
    c = result.content
    soup=BeautifulSoup(c,'lxml')
    return soup
'''
build urls group
'''
def build_urls(prefix,suffix):
    urls=[]
    for item in suffix:
        url=prefix+item
        urls.append(url)
    return urls
'''
acquire all the page titles and links and save it
'''
def find_title_link(soup):
    titles=[]
    links=[]
    try:
        contanier=soup.find('div',{'class':'container_padd'})
        ajaxtable=contanier.find('form',{'id':'ajaxtable'})
        page_list=ajaxtable.find_all('li')
        for page in page_list:
            titlelink=page.find('a',{'class':'truetit'})
            if titlelink.text==None:
                title=titlelink.find('b').text
            else:
                title=titlelink.text
            if np.random.uniform(0,1)>0.90:
                link=titlelink.get('href')
                titles.append(title)
                links.append(link)
    except:
        print('have none value')
    return titles,links


'''
acquire reply in every topic of 10 page
'''
def find_reply(soup):
    replys=[]
    try:
        details=soup.find('div',{'class':'hp-wrap details'})
        form=details.find('form')
        floors=form.find_all('div',{'class':'floor'})
        for floor in floors:
            table=floor.find('table',{'class':'case'})
            if floor.id!='tpc':
                if table.find('p')!=None:
                    reply=table.find('p').text
                else:
                    reply=table.find('td').text
                replys.append(reply)
            elif floor.id=='tpc':
                continue
    except:
        return None
    return replys


'''
acquire information from hupu pubg bbs
'''
url='https://bbs.hupu.com/pubg'
page_suffix=['','-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']
urls=build_urls(url,page_suffix)

title_group=[]
link_group=[]
for url in urls:
    soup=creat_bs(url)
    titles,links=find_title_link(soup)
    for title in titles:
        title_group.append(title)
    for link in links:
        link_group.append(link)


reply_urls=build_urls('https://bbs.hupu.com',link_group)
reply_group=[]
for url in reply_urls:
    soup=creat_bs(url)
    replys=find_reply(soup)
    if replys!=None:
        for reply in replys:
            reply_group.append(reply)


'''
creat wordlist and save as txt
'''
wordlist=str()
for title in title_group:
    wordlist+=title

for reply in reply_group:
    wordlist+=reply

def savetxt(wordlist):
    f=open('wordlist.txt','wb')
    f.write(wordlist.encode('utf8'))
    f.close()
savetxt(wordlist)