在scrapy中使用phantomJS实现异步爬取
使用selenium能够非常方便的获取网页的ajax内容，并且能够模拟用户点击和输入文本等诸多操作，这在使用scrapy爬取网页的过程中非常有用。网上将selenium集成到scrapy的文章很多，但是很少有能够实现异步爬取的，下面这段代码就重写了scrapy的downloader，同时实现了selenium的集成以及异步。使用时需要PhantomJSDownloadHandler添加到配置文件的DOWNLOADER中。 --------------------- 本文来自 郎总 的CSDN 博客 ，全文地址请点击：https://blog.csdn.net/whueratsjtuer/article/details/79198863?utm_source=copy
# encoding: utf-8
from __future__ import unicode_literals
from scrapy import signals
from scrapy.signalmanager import SignalManager
from scrapy.responsetypes import responsetypes
from scrapy.xlib.pydispatch import dispatcher
from selenium import webdriver
from six.moves import queue
from twisted.internet import defer, threads
from twisted.python.failure import Failure
class PhantomJSDownloadHandler(object):
def __init__(self, settings):
self.options = settings.get('PHANTOMJS_OPTIONS', {})
max_run = settings.get('PHANTOMJS_MAXRUN', 10)
self.sem = defer.DeferredSemaphore(max_run)
self.queue = queue.LifoQueue(max_run)
SignalManager(dispatcher.Any).connect(self._close, signal=signals.spider_closed)
def download_request(self, request, spider):
"""use semaphore to guard a phantomjs pool"""
return self.sem.run(self._wait_request, request, spider)
def _wait_request(self, request, spider):
try:
driver = self.queue.get_nowait()
except queue.Empty:
driver = webdriver.PhantomJS(**self.options)
driver.get(request.url)
# ghostdriver won't response when switch window until page is loaded
dfd = threads.deferToThread(lambda: driver.switch_to.window(driver.current_window_handle))
dfd.addCallback(self._response, driver, spider)
return dfd
def _response(self, _, driver, spider):
body = driver.execute_script("return document.documentElement.innerHTML")
if body.startswith("<head></head>"): # cannot access response header in Selenium
body = driver.execute_script("return document.documentElement.textContent")
url = driver.current_url
respcls = responsetypes.from_args(url=url, body=body[:100].encode('utf8'))
resp = respcls(url=url, body=body, encoding="utf-8")
response_failed = getattr(spider, "response_failed", None)
if response_failed and callable(response_failed) and response_failed(resp, driver):
driver.close()
return defer.fail(Failure())
else:
self.queue.put(driver)
return defer.succeed(resp)
def _close(self):
while not self.queue.empty():
driver = self.queue.get_nowait()
driver.close()
