forked from moyy996/AVDC
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathjavdb.py
executable file
·150 lines (148 loc) · 8.42 KB
/
javdb.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
import re
from lxml import etree
import json
from bs4 import BeautifulSoup
from ADC_function import *
def getTitle(a):
try:
html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('/html/body/section/div/h2/strong/text()')).strip(" ['']")
return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', '').replace(' : ', ''))
except:
return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', ''))
def getActor(a): # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',').replace(',', ', ')
def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
a = actor.split(',')
d={}
for i in a:
p={i:''}
d.update(p)
return d
def getStudio(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def getRuntime(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').rstrip('mi')
def getLabel(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def getNum(a):
html = etree.fromstring(a, etree.HTMLParser())
result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result2 + result1).strip('+')
def getYear(getRelease):
try:
result = str(re.search('\d{4}', getRelease).group())
return result
except:
return getRelease
def getRelease(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+')
def getTag(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',')
def getCover_small(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result = 'http:' + html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\'][1]/a['
'@class=\'box\']/div[@class=\'item-image fix-scale-cover\']/img/@src')[0]
return result
def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/section/div/div[@class=\'columns item-content\']/div[@class=\'column column-video-cover\']/a/img/@src')).strip(" ['']")
return result
def getDirector(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def getOutline(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
return result
def main(number):
number = number.upper()
try:
a = get_html('https://javdb.com/search?q=' + number + '&f=all').replace(u'\xa0', u' ')
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = html.xpath('//*[@id="videos"]/div/div/a/@href')[0]
b = get_html('https://javdb.com' + result1).replace(u'\xa0', u' ')
dic = {
'actor': getActor(b),
'title': getTitle(b).replace("\\n", '').replace(' ', '').replace(getActor(a), '').replace(getNum(a),
'').replace(
'无码', '').replace('有码', '').lstrip(' ').replace(number,''),
'studio': getStudio(b),
'outline': getOutline(b),
'runtime': getRuntime(b),
'director': getDirector(b),
'release': getRelease(b),
'number': getNum(b),
'cover': getCover(b),
'cover_small': getCover_small(a),
'imagecut': 3,
'tag': getTag(b),
'label': getLabel(b),
'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': getActorPhoto(getActor(b)),
'website': 'https://javdb.com' + result1,
'source': 'javdb.py',
}
if getNum(b) != number: # 与搜索到的番号不匹配
dic['title'] = ''
dic['number'] = ''
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
except:
a = get_html('https://javdb.com/search?q=' + number + '&f=all').replace(u'\xa0', u' ')
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = html.xpath('//*[@id="videos"]/div/div/a/@href')[0]
print(html.xpath('//*[@id="videos"]/div/div/a/@href'))
b = get_html('https://javdb.com' + result1).replace(u'\xa0', u' ')
dic = {
'actor': getActor(b),
'title': getTitle(b).replace("\\n", '').replace(' ', '').replace(getActor(a), '').replace(
getNum(b),
'').replace(
'无码', '').replace('有码', '').lstrip(' ').replace(number,''),
'studio': getStudio(b),
'outline': getOutline(b),
'runtime': getRuntime(b),
'director': getDirector(b),
'release': getRelease(b),
'number': getNum(b),
'cover': getCover(b),
'cover_small': getCover_small(a),
'imagecut': 3,
'tag': getTag(b),
'label': getLabel(b),
'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': getActorPhoto(getActor(b)),
'website': 'https://javdb.com' + result1,
'source': 'javdb.py',
}
if getNum(b) != number: # 与搜索到的番号不匹配
dic['title'] = ''
dic['number'] = ''
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
# main('DV-1562')
# input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。")
# print(get_html('https://javdb1.com/v/WwZ0Q'))