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
| import scrapy
from scrapy_splash import SplashRequest
import ppt.items as items
from scrapy.loader import ItemLoader
import urllib
import os
class BeautySpider(scrapy.Spider):
JPG = '.jpg'
PNG = '.png'
IMAGE_FOLDER = 'images'
IMAGE_MAX = 5
name = 'beauty'
allowed_domains = ['www.ptt.cc']
URL_ENTRY = 'https://www.ptt.cc/bbs/Beauty/index.html'
index = 1
script_1st = '''
function main(splash, args)
splash:on_request(function(request)
if request.url:find('css') then
request.abort()
end
end)
splash.images_enabled = false
-- need run js for click --
-- splash.js_enabled = false --
assert(splash:go(args.url))
assert(splash:wait(0.5))
local element = splash:select('.over18-button-container > button')
element:mouse_click()
assert(splash:wait(1))
return {
cookies = splash:get_cookies(),
html = splash:html(),
}
end
'''
script_2nd = '''
function main(splash, args)
splash:init_cookies(splash.args.cookies)
splash:on_request(function(request)
if request.url:find('css') then
request.abort()
end
end)
splash.images_enabled = false
-- need run js for click --
-- splash.js_enabled = false --
assert(splash:go(args.url))
assert(splash:wait(0.5))
assert(splash:wait(1))
return {
cookies = splash:get_cookies(),
html = splash:html(),
}
end
'''
def start_requests(self):
yield SplashRequest(url=self.URL_ENTRY,
callback=self.parse,
endpoint='execute',
args={'lua_source': self.script_1st})
def parse(self, response):
self.cookies = response.data['cookies']
posts = response.xpath("//div[@class='r-ent']")
for post in posts:
beaudy_item = items.PptBeautyItem()
beaudy_item['title'] = post.xpath(".//div[@class='title']/a/text()").get()
beaudy_item['url'] = post.xpath(".//div[@class='title']/a/@href").get()
beaudy_item['push_count'] = post.xpath(".//div[@class='nrec']/span/text()").get()
beaudy_item['author'] = post.xpath(".//div[@class='author']/text()").get()
if beaudy_item['title']:
if '公告' not in beaudy_item['title']:
yield SplashRequest(url=response.urljoin(beaudy_item['url']),
callback=self.post_parse,
endpoint='execute',
args={'lua_source': self.script_2nd},
cookies = self.cookies
)
def post_parse(self, response):
self.cookies = response.data['cookies']
if self.index < self.IMAGE_MAX:
title = response.xpath("(//div[@class='article-metaline']//span[@class='article-meta-value'])[2]/text()").get()
lists = response.xpath("//div[@class='richcontent']")
list_index = 1
for list in lists:
image_url = list.xpath(".//img/@src").get()
loader = ItemLoader(item=items.PptPostItem())
loader.add_value('image_urls', [image_url])
loader.add_value('index', self.index)
if self.PNG in image_url:
file_name = f"{title}{list_index}{self.PNG}"
elif self.JPG in image_url:
file_name = f"{title}{list_index}{self.JPG}"
else:
file_name = f"{title}{list_index}None{self.JPG}"
list_index += 1
self.image_download(image_url, file_name, self.IMAGE_FOLDER)
self.index += 1
yield loader.load_item()
if self.index > self.IMAGE_MAX:
break
def image_download(self, url, name, folder):
dir=os.path.abspath(folder)
work_path=os.path.join(dir,name)
urllib.request.urlretrieve(url, work_path)
|
