1 # -*- coding: utf-8 -*-
 2 
 3 # Define here the models for your scraped items
 4 #
 5 # See documentation in:
 6 # //docs.scrapy.org/en/latest/topics/items.html
 7 
 8 import scrapy
 9 
10 
11 class ScrapydemoItem(scrapy.Item):
12     # define the fields for your item here like:
13     # name = scrapy.Field()
14     pass

  1 # -*- coding: utf-8 -*-
  2 
  3 # Define here the models for your spider middleware
  4 #
  5 # See documentation in:
  6 # //docs.scrapy.org/en/latest/topics/spider-middleware.html
  7 
  8 from scrapy import signals
  9 
 10 
 11 class ScrapydemoSpiderMiddleware(object):
 12     # Not all methods need to be defined. If a method is not defined,
 13     # scrapy acts as if the spider middleware does not modify the
 14     # passed objects.
 15 
 16     @classmethod
 17     def from_crawler(cls, crawler):
 18         # This method is used by Scrapy to create your spiders.
 19         s = cls()
 20         crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
 21         return s
 22 
 23     def process_spider_input(self, response, spider):
 24         # Called for each response that goes through the spider
 25         # middleware and into the spider.
 26 
 27         # Should return None or raise an exception.
 28         return None
 29 
 30     def process_spider_output(self, response, result, spider):
 31         # Called with the results returned from the Spider, after
 32         # it has processed the response.
 33 
 34         # Must return an iterable of Request, dict or Item objects.
 35         for i in result:
 36             yield i
 37 
 38     def process_spider_exception(self, response, exception, spider):
 39         # Called when a spider or process_spider_input() method
 40         # (from other spider middleware) raises an exception.
 41 
 42         # Should return either None or an iterable of Request, dict
 43         # or Item objects.
 44         pass
 45 
 46     def process_start_requests(self, start_requests, spider):
 47         # Called with the start requests of the spider, and works
 48         # similarly to the process_spider_output() method, except
 49         # that it doesn』t have a response associated.
 50 
 51         # Must return only requests (not items).
 52         for r in start_requests:
 53             yield r
 54 
 55     def spider_opened(self, spider):
 56         spider.logger.info('Spider opened: %s' % spider.name)
 57 
 58 
 59 class ScrapydemoDownloaderMiddleware(object):
 60     # Not all methods need to be defined. If a method is not defined,
 61     # scrapy acts as if the downloader middleware does not modify the
 62     # passed objects.
 63 
 64     @classmethod
 65     def from_crawler(cls, crawler):
 66         # This method is used by Scrapy to create your spiders.
 67         s = cls()
 68         crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
 69         return s
 70 
 71     def process_request(self, request, spider):
 72         # Called for each request that goes through the downloader
 73         # middleware.
 74 
 75         # Must either:
 76         # - return None: continue processing this request
 77         # - or return a Response object
 78         # - or return a Request object
 79         # - or raise IgnoreRequest: process_exception() methods of
 80         #   installed downloader middleware will be called
 81         return None
 82 
 83     def process_response(self, request, response, spider):
 84         # Called with the response returned from the downloader.
 85 
 86         # Must either;
 87         # - return a Response object
 88         # - return a Request object
 89         # - or raise IgnoreRequest
 90         return response
 91 
 92     def process_exception(self, request, exception, spider):
 93         # Called when a download handler or a process_request()
 94         # (from other downloader middleware) raises an exception.
 95 
 96         # Must either:
 97         # - return None: continue processing this exception
 98         # - return a Response object: stops process_exception() chain
 99         # - return a Request object: stops process_exception() chain
100         pass
101 
102     def spider_opened(self, spider):
103         spider.logger.info('Spider opened: %s' % spider.name)

 1 # -*- coding: utf-8 -*-
 2 
 3 # Define your item pipelines here
 4 #
 5 # Don't forget to add your pipeline to the ITEM_PIPELINES setting
 6 # See: //docs.scrapy.org/en/latest/topics/item-pipeline.html
 7 
 8 
 9 class ScrapydemoPipeline(object):
10     def process_item(self, item, spider):
11         return item

 1 # -*- coding: utf-8 -*-
 2 
 3 # Scrapy settings for scrapyDemo project
 4 #
 5 # For simplicity, this file contains only settings considered important or
 6 # commonly used. You can find more settings consulting the documentation:
 7 #
 8 #     //docs.scrapy.org/en/latest/topics/settings.html
 9 #     //docs.scrapy.org/en/latest/topics/downloader-middleware.html
10 #     //docs.scrapy.org/en/latest/topics/spider-middleware.html
11 
12 BOT_NAME = 'scrapyDemo'
13 
14 SPIDER_MODULES = ['scrapyDemo.spiders']
15 NEWSPIDER_MODULE = 'scrapyDemo.spiders'
16 
17 
18 # Crawl responsibly by identifying yourself (and your website) on the user-agent
19 #USER_AGENT = 'scrapyDemo (+//www.yourdomain.com)'
20 
21 # Obey robots.txt rules
22 ROBOTSTXT_OBEY = True
23 
24 # Configure maximum concurrent requests performed by Scrapy (default: 16)
25 #CONCURRENT_REQUESTS = 32
26 
27 # Configure a delay for requests for the same website (default: 0)
28 # See //docs.scrapy.org/en/latest/topics/settings.html#download-delay
29 # See also autothrottle settings and docs
30 #DOWNLOAD_DELAY = 3
31 # The download delay setting will honor only one of:
32 #CONCURRENT_REQUESTS_PER_DOMAIN = 16
33 #CONCURRENT_REQUESTS_PER_IP = 16
34 
35 # Disable cookies (enabled by default)
36 #COOKIES_ENABLED = False
37 
38 # Disable Telnet Console (enabled by default)
39 #TELNETCONSOLE_ENABLED = False
40 
41 # Override the default request headers:
42 #DEFAULT_REQUEST_HEADERS = {
43 #   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
44 #   'Accept-Language': 'en',
45 #}
46 
47 # Enable or disable spider middlewares
48 # See //docs.scrapy.org/en/latest/topics/spider-middleware.html
49 #SPIDER_MIDDLEWARES = {
50 #    'scrapyDemo.middlewares.ScrapydemoSpiderMiddleware': 543,
51 #}
52 
53 # Enable or disable downloader middlewares
54 # See //docs.scrapy.org/en/latest/topics/downloader-middleware.html
55 #DOWNLOADER_MIDDLEWARES = {
56 #    'scrapyDemo.middlewares.ScrapydemoDownloaderMiddleware': 543,
57 #}
58 
59 # Enable or disable extensions
60 # See //docs.scrapy.org/en/latest/topics/extensions.html
61 #EXTENSIONS = {
62 #    'scrapy.extensions.telnet.TelnetConsole': None,
63 #}
64 
65 # Configure item pipelines
66 # See //docs.scrapy.org/en/latest/topics/item-pipeline.html
67 #ITEM_PIPELINES = {
68 #    'scrapyDemo.pipelines.ScrapydemoPipeline': 300,
69 #}
70 
71 # Enable and configure the AutoThrottle extension (disabled by default)
72 # See //docs.scrapy.org/en/latest/topics/autothrottle.html
73 #AUTOTHROTTLE_ENABLED = True
74 # The initial download delay
75 #AUTOTHROTTLE_START_DELAY = 5
76 # The maximum download delay to be set in case of high latencies
77 #AUTOTHROTTLE_MAX_DELAY = 60
78 # The average number of requests Scrapy should be sending in parallel to
79 # each remote server
80 #AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
81 # Enable showing throttling stats for every response received:
82 #AUTOTHROTTLE_DEBUG = False
83 
84 # Enable and configure HTTP caching (disabled by default)
85 # See //docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
86 #HTTPCACHE_ENABLED = True
87 #HTTPCACHE_EXPIRATION_SECS = 0
88 #HTTPCACHE_DIR = 'httpcache'
89 #HTTPCACHE_IGNORE_HTTP_CODES = []
90 #HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'