# middlewares.py
from scrapy import signals
from scrapy.http import Response
from scrapy.exceptions import IgnoreRequest
import selenium
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
class Pic4KgirlDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.
    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.
        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        try:
            self.browser=selenium.webdriver.Chrome()
            self.wait=WebDriverWait(self.browser,10)
            self.browser.get(request.url)
            self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#main > div.page > a:nth-child(10)')))
            return Response(url=request.url,status=200,request=request,body=self.browser.page_source.encode('utf-8'))
        #except:
            #raise IgnoreRequest()
        finally:
            self.browser.close()

@property
    def text(self):
        """For subclasses of TextResponse, this will return the body
        as text (unicode object in Python 2 and str in Python 3)
        """
        raise AttributeError("Response content isn't text")
    def css(self, *a, **kw):
        """Shortcut method implemented only by responses whose content
        is text (subclasses of TextResponse).
        """
        raise NotSupported("Response content isn't text")
    def xpath(self, *a, **kw):
        """Shortcut method implemented only by responses whose content
        is text (subclasses of TextResponse).
        """
        raise NotSupported("Response content isn't text")

**TextResponse對(duì)象**
class scrapy.http.TextResponse(url[, encoding[, ...]])
**HtmlResponse對(duì)象**
class scrapy.http.HtmlResponse(url[, ...])
**XmlResponse對(duì)象**
class scrapy.http.XmlResponse（url [，... ] ）

class TextResponse(Response):
    _DEFAULT_ENCODING = 'ascii'
    def __init__(self, *args, **kwargs):
        self._encoding = kwargs.pop('encoding', None)
        self._cached_benc = None
        self._cached_ubody = None
        self._cached_selector = None
        super(TextResponse, self).__init__(*args, **kwargs)

@property
    def selector(self):
        from scrapy.selector import Selector
        if self._cached_selector is None:
            self._cached_selector = Selector(self)
        return self._cached_selector
    def xpath(self, query, **kwargs):
        return self.selector.xpath(query, **kwargs)
    def css(self, query):
        return self.selector.css(query)