forked from mvdctop/Movie_Data_Capture
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathjavbus.py
executable file
·176 lines (172 loc) · 6.74 KB
/
javbus.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
167
168
169
170
171
172
173
174
175
176
import re
from pyquery import PyQuery as pq#need install
from lxml import etree#need install
from bs4 import BeautifulSoup#need install
import json
from ADC_function import *
import fanza
def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
soup = BeautifulSoup(htmlcode, 'lxml')
a = soup.find_all(attrs={'class': 'star-name'})
d={}
for i in a:
l=i.a['href']
t=i.get_text()
html = etree.fromstring(get_html(l), etree.HTMLParser())
p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
p2={t:p}
d.update(p2)
return d
def getTitle(htmlcode): #获取标题
doc = pq(htmlcode)
title=str(doc('div.container h3').text()).replace(' ','-')
try:
title2 = re.sub('n\d+-','',title)
return title2
except:
return title
def getStudio(htmlcode): #获取厂商
html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
return result
def getYear(htmlcode): #获取年份
html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
return result
def getCover(htmlcode): #获取封面链接
doc = pq(htmlcode)
image = doc('a.bigImage')
return image.attr('href')
def getRelease(htmlcode): #获取出版日期
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
return result
def getRuntime(htmlcode): #获取分钟
soup = BeautifulSoup(htmlcode, 'lxml')
a = soup.find(text=re.compile('分鐘'))
return a
def getActor(htmlcode): #获取女优
b=[]
soup=BeautifulSoup(htmlcode,'lxml')
a=soup.find_all(attrs={'class':'star-name'})
for i in a:
b.append(i.get_text())
return b
def getNum(htmlcode): #获取番号
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
return result
def getDirector(htmlcode): #获取导演
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
return result
def getCID(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
#print(htmlcode)
string = html.xpath("//a[contains(@class,'sample-box')][1]/@href")[0].replace('https://pics.dmm.co.jp/digital/video/','')
result = re.sub('/.*?.jpg','',string)
return result
def getOutline(htmlcode): #获取演员
html = etree.fromstring(htmlcode, etree.HTMLParser())
try:
result = html.xpath("string(//div[contains(@class,'mg-b20 lh4')])").replace('\n','')
return result
except:
return ''
def getSerise(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
return result
def getTag(htmlcode): # 获取演员
tag = []
soup = BeautifulSoup(htmlcode, 'lxml')
a = soup.find_all(attrs={'class': 'genre'})
for i in a:
if 'onmouseout' in str(i):
continue
tag.append(i.get_text())
return tag
def main_uncensored(number):
htmlcode = get_html('https://www.javbus.com/' + number)
if getTitle(htmlcode) == '':
htmlcode = get_html('https://www.javbus.com/' + number.replace('-','_'))
try:
dww_htmlcode = fanza.main_htmlcode(getCID(htmlcode))
except:
dww_htmlcode = ''
dic = {
'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
'studio': getStudio(htmlcode),
'year': getYear(htmlcode),
'outline': getOutline(dww_htmlcode),
'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode),
'actor': getActor(htmlcode),
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'cover': getCover(htmlcode),
'tag': getTag(htmlcode),
'label': getSerise(htmlcode),
'imagecut': 0,
'actor_photo': '',
'website': 'https://www.javbus.com/' + number,
'source': 'javbus.py',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
def main(number):
try:
try:
htmlcode = get_html('https://www.javbus.com/' + number)
if getTitle(htmlcode) == '':
raise Exception('direct link is invalid')
try:
dww_htmlcode = fanza.main_htmlcode(getCID(htmlcode))
except:
dww_htmlcode = ''
dic = {
'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
'studio': getStudio(htmlcode),
'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
'outline': getOutline(dww_htmlcode),
'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode),
'actor': getActor(htmlcode),
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'cover': getCover(htmlcode),
'imagecut': 1,
'tag': getTag(htmlcode),
'label': getSerise(htmlcode),
'actor_photo': getActorPhoto(htmlcode),
'website': 'https://www.javbus.com/' + number,
'source': 'javbus.py',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,
separators=(',', ':'), ) # .encode('UTF-8')
return js
except Exception as e1:
print (e1)
try:
print('Searching from https://www.javbus.com/search/' + number)
new_pattern = re.compile(number + '_20\d{2}-\d{2}-\d{2}', flags = re.I)
search_query = get_html('https://www.javbus.com/search/' + number + '&type=&parent=ce')
new_number = re.findall(new_pattern, search_query)
if len(new_number)>0:
print(new_number)
k = input('choose which film to scrap:')
return main(new_number[int(k)])
else:
raise Exception('no results for censored file')
except Exception as e2:
print(e2)
print('Searching for the uncensored site')
return main_uncensored(number)
except:
data = {
"title": "",
}
js = json.dumps(
data, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ":")
)
return js