blob: 38f18631696296f33ff96997aa64683947fbe398 (
plain)
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
|
# -*- coding: utf-8 -*-
import scrapy
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy import Selector
import datetime
from database.models import Neodarznet
from dateutil.relativedelta import *
import logging
class NeodarznetSpider(CrawlSpider):
name = "neodarznet_updater"
custom_settings = {
'ITEM_PIPELINES': {
'crawler.neodarznet.pipelines.NeodarznetPipeline': 0
}
}
allow_domains = ['neodarz.net']
datas = Neodarznet.select(Neodarznet.url).dicts()
datas_array = []
for value in datas:
datas_array.append(value['url'])
start_urls = datas_array
def start_requests(self):
for url in self.start_urls:
logging.info(url)
try:
page = Neodarznet.get(Neodarznet.url == url)
if page.date_updated < datetime.datetime.now()+relativedelta(weeks=-1):
yield scrapy.Request(url, callback=self.parse_url, dont_filter=True)
except Neodarznet.DoesNotExist:
yield scrapy.Request(url, callback=self.parse_url, dont_filter=True)
continue
def parse_url(self, response):
sel = Selector(response)
yield {
'url': response.url,
'title': response.css('title::text').extract_first(),
'content': ''.join(sel.select("//div[@class='bodya']//text()").extract()).strip(),
'content_length': len(response.body),
'date_updated': datetime.datetime.now()
}
|
