这篇文章给大家介绍怎么在scrapy中利用phantomJS实现异步爬取，内容非常详细，感兴趣的小伙伴们可以参考借鉴，希望对大家能有所帮助。
使用时需要PhantomJSDownloadHandler添加到配置文件的DOWNLOADER中。
# 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()关于怎么在scrapy中利用phantomJS实现异步爬取就分享到这里了，希望以上内容可以对大家有一定的帮助，可以学到更多知识。如果觉得文章不错，可以把它分享出去让更多的人看到。
免责声明：本站发布的内容（图片、视频和文字）以原创、转载和分享为主，文章观点不代表本网站立场，如果涉及侵权请联系站长邮箱：is@yisu.com进行举报，并提供相关证据，一经查实，将立刻删除涉嫌侵权内容。
