forked from mvdctop/Movie_Data_Capture
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmgstage.py
executable file
·120 lines (118 loc) · 6.71 KB
/
mgstage.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
import re
from lxml import etree
import json
from bs4 import BeautifulSoup
from ADC_function import *
# import sys
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
def getTitle(a):
try:
html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('//*[@id="center_column"]/div[1]/h1/text()')).strip(" ['']")
return result.replace('/', ',')
except:
return ''
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('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
result2=str(html.xpath('//th[contains(text(),"出演：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
return str(result1+result2).strip('+').replace("', '",'').replace('"','').replace('/',',')
def getStudio(a):
html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
result1=str(html.xpath('//th[contains(text(),"メーカー：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
result2=str(html.xpath('//th[contains(text(),"メーカー：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
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('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
result2 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
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('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
result2 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
def getNum(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
return str(result1 + result2).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('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
result2 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
return str(result1 + result2).strip('+').replace('/','-')
def getTag(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
result2 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
return str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','').replace(',,','').split(',')
def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="center_column"]/div[1]/div[1]/div/div/h2/img/@src')).strip(" ['']")
# /html/body/div[2]/article[2]/div[1]/div[1]/div/div/h2/img/@src
return result
def getDirector(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
def getOutline(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//p/text()')).strip(" ['']").replace(u'\\n', '').replace("', '', '", '')
return result
def getSeries(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def main(number2):
number=number2.upper()
htmlcode=str(get_html('https://www.mgstage.com/product/product_detail/'+str(number)+'/',cookies={'adc':'1'}))
soup = BeautifulSoup(htmlcode, 'lxml')
a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
b = str(soup.find(attrs={'id': 'introduction'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
#print(b)
dic = {
'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''),
'studio': getStudio(a),
'outline': getOutline(b),
'runtime': getRuntime(a),
'director': getDirector(a),
'actor': getActor(a),
'release': getRelease(a),
'number': getNum(a),
'cover': getCover(htmlcode),
'imagecut': 0,
'tag': getTag(a),
'label':getLabel(a),
'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': '',
'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
'source': 'mgstage.py',
'series': getSeries(a),
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
#print(htmlcode)
if __name__ == '__main__':
print(main('SIRO-4149'))