forked from mvdctop/Movie_Data_Capture
-
Notifications
You must be signed in to change notification settings - Fork 0
/
fc2fans_club.py
executable file
·157 lines (152 loc) · 7.46 KB
/
fc2fans_club.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
import re
from lxml import etree#need install
import json
import ADC_function
# import sys
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
def getTitle(htmlcode): #获取厂商
#print(htmlcode)
html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('/html/body/div[2]/div/div[1]/h3/text()')).strip(" ['']")
result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
#print(result2)
return result2
def getActor(htmlcode):
try:
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[5]/a/text()')).strip(" ['']")
return result
except:
return ''
def getStudio(htmlcode): #获取厂商
html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
return result
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(" ['']")
#print(result)
return result
def getRelease(htmlcode2): #
#a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
html=etree.fromstring(htmlcode2,etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
return result
def getCover(htmlcode,number,htmlcode2): #获取厂商 #
#a = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id=' + str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") + '&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
html = etree.fromstring(htmlcode2, etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
if result == '':
html = etree.fromstring(htmlcode, etree.HTMLParser())
result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']")
return 'https://fc2club.com' + result2
return 'http:' + result
def getOutline(htmlcode2): #获取番号 #
html = etree.fromstring(htmlcode2, etree.HTMLParser())
result = str(html.xpath('/html/body/div[1]/div[2]/div[2]/div[1]/div/article/section[4]/p/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
return result
def getTag(htmlcode): #获取番号
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
return result.strip(" ['']").replace("'",'').replace(' ','')
def getYear(release):
try:
result = re.search('\d{4}',release).group()
return result
except:
return ''
def getTitle_fc2com(htmlcode): #获取厂商
html = etree.fromstring(htmlcode,etree.HTMLParser())
result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/h3/text()')[0]
return result
def getActor_fc2com(htmlcode):
try:
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')[0]
return result
except:
return ''
def getStudio_fc2com(htmlcode): #获取厂商
try:
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')).strip(" ['']")
return result
except:
return ''
def getNum_fc2com(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 getRelease_fc2com(htmlcode2): #
html=etree.fromstring(htmlcode2,etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
return result
def getCover_fc2com(htmlcode2): #获取厂商 #
html = etree.fromstring(htmlcode2, etree.HTMLParser())
result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[1]/span/img/@src')).strip(" ['']")
return 'http:' + result
def getOutline_fc2com(htmlcode2): #获取番号 #
html = etree.fromstring(htmlcode2, etree.HTMLParser())
result = str(html.xpath('/html/body/div/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
return result
def getTag_fc2com(number): #获取番号
htmlcode = str(bytes(ADC_function.get_html('http://adult.contents.fc2.com/api/v4/article/'+number+'/tag?'),'utf-8').decode('unicode-escape'))
result = re.findall('"tag":"(.*?)"', htmlcode)
return result
def getYear_fc2com(release):
try:
result = re.search('\d{4}',release).group()
return result
except:
return ''
def main(number):
htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/'+number+'/')
htmlcode = ADC_function.get_html('https://fc2club.com//html/FC2-' + number + '.html')
actor = getActor(htmlcode)
if getActor(htmlcode) == '':
actor = 'FC2系列'
dic = {
'title': getTitle(htmlcode),
'studio': getStudio(htmlcode),
'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
'outline': '',#getOutline(htmlcode2),
'runtime': getYear(getRelease(htmlcode)),
'director': getStudio(htmlcode),
'actor': actor,
'release': getRelease(number),
'number': 'FC2-'+number,
'label': '',
'cover': getCover(htmlcode,number,htmlcode2),
'imagecut': 0,
'tag': getTag(htmlcode),
'actor_photo':'',
'website': 'https://fc2club.com//html/FC2-' + number + '.html',
'source':'https://fc2club.com//html/FC2-' + number + '.html',
}
if dic['title'] == '':
htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/' + number + '/',cookies={'wei6H':'1'})
actor = getActor(htmlcode)
if getActor(htmlcode) == '':
actor = 'FC2系列'
dic = {
'title': getTitle_fc2com(htmlcode2),
'studio': getStudio_fc2com(htmlcode2),
'year': '', # str(re.search('\d{4}',getRelease(number)).group()),
'outline': getOutline_fc2com(htmlcode2),
'runtime': getYear_fc2com(getRelease(htmlcode2)),
'director': getStudio_fc2com(htmlcode2),
'actor': actor,
'release': getRelease_fc2com(number),
'number': 'FC2-' + number,
'cover': getCover_fc2com(htmlcode2),
'imagecut': 0,
'tag': getTag_fc2com(number),
'label': '',
'actor_photo': '',
'website': 'http://adult.contents.fc2.com/article/' + number + '/',
'source': 'http://adult.contents.fc2.com/article/' + number + '/',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
return js
#print(main('1252953'))