|
| 1 | +# -*- coding: utf-8 -*- |
| 2 | + |
| 3 | +# Define here the models for your spider middleware |
| 4 | +# |
| 5 | +# See documentation in: |
| 6 | +# https://doc.scrapy.org/en/latest/topics/spider-middleware.html |
| 7 | + |
| 8 | +from scrapy import signals |
| 9 | +from scrapy.http import HtmlResponse |
| 10 | + |
| 11 | +from selenium import webdriver |
| 12 | +from selenium.common.exceptions import TimeoutException |
| 13 | + |
| 14 | + |
| 15 | +class Image360SpiderMiddleware(object): |
| 16 | + # Not all methods need to be defined. If a method is not defined, |
| 17 | + # scrapy acts as if the spider middleware does not modify the |
| 18 | + # passed objects. |
| 19 | + |
| 20 | + @classmethod |
| 21 | + def from_crawler(cls, crawler): |
| 22 | + # This method is used by Scrapy to create your spiders. |
| 23 | + s = cls() |
| 24 | + crawler.signals.connect(s.spider_opened, signal=signals.spider_opened) |
| 25 | + return s |
| 26 | + |
| 27 | + def process_spider_input(self, response, spider): |
| 28 | + # Called for each response that goes through the spider |
| 29 | + # middleware and into the spider. |
| 30 | + |
| 31 | + # Should return None or raise an exception. |
| 32 | + return None |
| 33 | + |
| 34 | + def process_spider_output(self, response, result, spider): |
| 35 | + # Called with the results returned from the Spider, after |
| 36 | + # it has processed the response. |
| 37 | + |
| 38 | + # Must return an iterable of Request, dict or Item objects. |
| 39 | + for i in result: |
| 40 | + yield i |
| 41 | + |
| 42 | + def process_spider_exception(self, response, exception, spider): |
| 43 | + # Called when a spider or process_spider_input() method |
| 44 | + # (from other spider middleware) raises an exception. |
| 45 | + |
| 46 | + # Should return either None or an iterable of Response, dict |
| 47 | + # or Item objects. |
| 48 | + pass |
| 49 | + |
| 50 | + def process_start_requests(self, start_requests, spider): |
| 51 | + # Called with the start requests of the spider, and works |
| 52 | + # similarly to the process_spider_output() method, except |
| 53 | + # that it doesn’t have a response associated. |
| 54 | + |
| 55 | + # Must return only requests (not items). |
| 56 | + for r in start_requests: |
| 57 | + yield r |
| 58 | + |
| 59 | + def spider_opened(self, spider): |
| 60 | + spider.logger.info('Spider opened: %s' % spider.name) |
| 61 | + |
| 62 | + |
| 63 | +class Image360DownloaderMiddleware(object): |
| 64 | + # Not all methods need to be defined. If a method is not defined, |
| 65 | + # scrapy acts as if the downloader middleware does not modify the |
| 66 | + # passed objects. |
| 67 | + |
| 68 | + @classmethod |
| 69 | + def from_crawler(cls, crawler): |
| 70 | + # This method is used by Scrapy to create your spiders. |
| 71 | + s = cls() |
| 72 | + crawler.signals.connect(s.spider_opened, signal=signals.spider_opened) |
| 73 | + return s |
| 74 | + |
| 75 | + def process_request(self, request, spider): |
| 76 | + # Called for each request that goes through the downloader |
| 77 | + # middleware. |
| 78 | + |
| 79 | + # Must either: |
| 80 | + # - return None: continue processing this request |
| 81 | + # - or return a Response object |
| 82 | + # - or return a Request object |
| 83 | + # - or raise IgnoreRequest: process_exception() methods of |
| 84 | + # installed downloader middleware will be called |
| 85 | + return None |
| 86 | + |
| 87 | + def process_response(self, request, response, spider): |
| 88 | + # Called with the response returned from the downloader. |
| 89 | + |
| 90 | + # Must either; |
| 91 | + # - return a Response object |
| 92 | + # - return a Request object |
| 93 | + # - or raise IgnoreRequest |
| 94 | + return response |
| 95 | + |
| 96 | + def process_exception(self, request, exception, spider): |
| 97 | + # Called when a download handler or a process_request() |
| 98 | + # (from other downloader middleware) raises an exception. |
| 99 | + |
| 100 | + # Must either: |
| 101 | + # - return None: continue processing this exception |
| 102 | + # - return a Response object: stops process_exception() chain |
| 103 | + # - return a Request object: stops process_exception() chain |
| 104 | + pass |
| 105 | + |
| 106 | + def spider_opened(self, spider): |
| 107 | + spider.logger.info('Spider opened: %s' % spider.name) |
| 108 | + |
| 109 | + |
| 110 | +class TaobaoDownloaderMiddleWare(object): |
| 111 | + |
| 112 | + def __init__(self, timeout=None): |
| 113 | + self.timeout = timeout |
| 114 | + self.browser = webdriver.Chrome() |
| 115 | + self.browser.set_window_size(1000, 600) |
| 116 | + self.browser.set_page_load_timeout(self.timeout) |
| 117 | + |
| 118 | + def __del__(self): |
| 119 | + self.browser.close() |
| 120 | + |
| 121 | + def process_request(self, request, spider): |
| 122 | + try: |
| 123 | + self.browser.get(request.url) |
| 124 | + return HtmlResponse(url=request.url, body=self.browser.page_source, |
| 125 | + request=request, encoding='utf-8', status=200) |
| 126 | + except TimeoutException: |
| 127 | + return HtmlResponse(url=request.url, status=500, request=request) |
| 128 | + |
| 129 | + def process_response(self, request, response, spider): |
| 130 | + return response |
| 131 | + |
| 132 | + def process_exception(self, request, exception, spider): |
| 133 | + pass |
| 134 | + |
| 135 | + @classmethod |
| 136 | + def from_crawler(cls, crawler): |
| 137 | + return cls(timeout=10) |
0 commit comments