scrapy和webkit

最新推荐文章于 2020-09-01 00:46:14 发布

chuiz777

最新推荐文章于 2020-09-01 00:46:14 发布

阅读量265

点赞数

本文链接：https://blog.csdn.net/qq_39959696/article/details/82494316

版权

#配置 downloader middleware


from scrapy.http import Request, FormRequest, HtmlResponse
 
import gtk
import webkit
import jswebkit
import settings
 
class WebkitDownloader( object ):
    def process_request( self, request, spider ):
        if spider.name in settings.WEBKIT_DOWNLOADER:
            if( type(request) is not FormRequest ):
                webview = webkit.WebView()
                webview.connect( 'load-finished', lambda v,f: gtk.main_quit() )
                webview.load_uri( request.url )
                gtk.main()
                js = jswebkit.JSContext( webview.get_main_frame().get_global_context() )
                renderedBody = str( js.EvaluateScript( 'document.body.innerHTML' ) )
                return HtmlResponse( request.url, body=renderedBody )

settings

#which spider should use WEBKIT
WEBKIT_DOWNLOADER=['ccb']
 
DOWNLOADER_MIDDLEWARES = {
    'rate_crawler.dowloader.WebkitDownloader': 543,
}   
 
import os
os.environ["DISPLAY"] = ":0"