我正在试图找出scrapy和泼水。作为练习,我尝试在下面的javascript网站上点击按钮:http://thestlbrowns.com/,然后返回新渲染页面的html。
我的代码如下所示:
import scrapy
import json
from scrapy import Request
class MySpider(scrapy.Spider):
name = 'spiderman'
domain = ['web']
start_urls = ['http://thestlbrowns.com/']
def start_requests(self):
script = """
function main(splash)
local url = splash.args.url
assert(splash:go(url))
assert(splash:wait(1))
assert(splash:runjs("$('#title.play-ball > a:first-child').click()"))
assert(splash:wait(1))
-- return result as a JSON object
return {
html = splash:html(),
-- we don't need screenshot or network activity
--png = splash:png(),
--har = splash:har(),
}
end
"""
for url in self.start_urls:
yield Request(url, self.parse, meta={'splash': {'args':{'lua_source': script},'endpoint':'execute',}})
def parse(self, response):
splash_json = json.loads(response.body_as_unicode())
但是,当我运行此代码时,我得到以下输出:
$ scrapy crawl spiderman
2017-01-12 14:19:03 [scrapy.utils.log] INFO: Scrapy 1.3.0 started (bot: myScrapingProject)
2017-01-12 14:19:03 [scrapy.utils.log] INFO: Overridden settings: {'BOT_NAME': 'myScrapingProject', 'DOWNLOAD_DELAY': 0.25, 'DUPEFILTER_CLASS': 'scrapy_splash.SplashAwareDupeFilter', 'HTTPCACHE_STORAGE': 'scrapy_splash.SplashAwareFSCacheStorage', 'NEWSPIDER_MODULE': 'myScrapingProject.spiders', 'SPIDER_MODULES': ['myScrapingProject.spiders'], 'USER_AGENT': 'Mozilla/5.0 (X11; Linux x86_64; rv:7.0.1) Gecko/20100101 Firefox/7.7'}
2017-01-12 14:19:03 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.logstats.LogStats']
2017-01-12 14:19:03 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
'scrapy.downloadermiddlewares.retry.RetryMiddleware',
'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
'scrapy_splash.SplashCookiesMiddleware',
'scrapy_splash.SplashMiddleware',
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2017-01-12 14:19:03 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy_splash.SplashDeduplicateArgsMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']
2017-01-12 14:19:03 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2017-01-12 14:19:03 [scrapy.core.engine] INFO: Spider opened
2017-01-12 14:19:03 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2017-01-12 14:19:03 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023
2017-01-12 14:19:16 [scrapy_splash.middleware] WARNING: Bad request to Splash: {'error': 400, 'info': {'error': "bad argument #2 to 'assert' (string expected, got table)", 'line_number': 8, 'source': '[string "..."]', 'message': 'Lua error: [string "..."]:8: bad argument #2 to \'assert\' (string expected, got table)', 'type': 'LUA_ERROR'}, 'description': 'Error happened while executing Lua script', 'type': 'ScriptError'}
2017-01-12 14:19:16 [scrapy.core.engine] DEBUG: Crawled (400) <POST http://localhost:8050/execute> (referer: None)
2017-01-12 14:19:16 [scrapy.spidermiddlewares.httperror] INFO: Ignoring response <400 http://thestlbrowns.com/>: HTTP status code is not handled or not allowed
2017-01-12 14:19:16 [scrapy.core.engine] INFO: Closing spider (finished)
2017-01-12 14:19:16 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 1222,
'downloader/request_count': 1,
'downloader/request_method_count/POST': 1,
'downloader/response_bytes': 471,
'downloader/response_count': 1,
'downloader/response_status_count/400': 1,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2017, 1, 12, 13, 19, 16, 846242),
'log_count/DEBUG': 2,
'log_count/INFO': 8,
'log_count/WARNING': 1,
'response_received_count': 1,
'scheduler/dequeued': 2,
'scheduler/dequeued/memory': 2,
'scheduler/enqueued': 2,
'scheduler/enqueued/memory': 2,
'splash/execute/request_count': 1,
'splash/execute/response_count/400': 1,
'start_time': datetime.datetime(2017, 1, 12, 13, 19, 3, 417278)}
2017-01-12 14:19:16 [scrapy.core.engine] INFO: Spider closed (finished)
问:有谁知道如何解决这个/我做错了什么?
编辑:当我在将脚本传递给splash之前添加script = quote(script)
时,我得到以下错误输出:
Message: 'Bad request to Splash: {\'type\': \'ScriptError\', \'description\': \'Error happened while executing Lua script\', ' \
'\'error\': 400, \'info\': {\'error\': "unexpected symbol near \'%\'", \'type\': \'LUA_INIT_ERROR\', \'line_number\': 1, ' \
'\'source\': \'[string "%0A%20%20%20%20%20%20%20%20%20function%20main..."]\',' \
' \'message\': \'[string "%0A%20%20%20%20%20%20%20%20%20function%20main..."]:1: unexpected symbol near \\\'%\\\'\'}}'
答案 0 :(得分:7)
Splash响应确实包含一些提示:
{'description': 'Error happened while executing Lua script',
'error': 400,
'info': {'error': "bad argument #2 to 'assert' (string expected, got table)",
'line_number': 8,
'message': 'Lua error: [string "..."]:8: bad argument #2 to \'assert\' (string expected, got table)',
'source': '[string "..."]',
'type': 'LUA_ERROR'},
'type': 'ScriptError'}
如果你在Splash的网络界面中尝试你的脚本(这是你的朋友!),你就会遇到同样的错误:
assert(splash:runjs("$('#title.play-ball > a:first-child').click()"))
如果你稍微更改了Lua脚本,那么就会发现错误(顺便说一下,我认为你的意思是.title.play-ball > a:first-child
,因为没有id="title"
的元素):
function main(splash)
local url = splash.args.url
assert(splash:go(url))
assert(splash:wait(1))
-- go back 1 month in time and wait a little (1 second)
ok, err = splash:runjs("$('.title.play-ball > a:first-child').click()")
assert(splash:wait(1))
-- return result as a JSON object
return {
html = splash:html(),
error = err
-- we don't need screenshot or network activity
--png = splash:png(),
--har = splash:har(),
}
end
并在Web界面中运行它,您会在响应中看到一个“错误”对象,其中显示:
error: Object
js_error: "ReferenceError: Can't find variable: $"
js_error_message: "Can't find variable: $"
js_error_type: "ReferenceError"
message: "JS error: \"ReferenceError: Can't find variable: $\""
splash_method: "runjs"
type: "JS_ERROR"
$
魔法似乎无法在该网站上运行。例如,您可以在Chrome控制台中使用它,但是使用Splash,您可能/显然需要加载jQuery(或类似的东西),通常使用splash:autoload
。例如:
function main(splash)
assert(splash:autoload("https://code.jquery.com/jquery-3.1.1.min.js"))
local url = splash.args.url
assert(splash:go(url))
assert(splash:wait(1))
-- go back 1 month in time and wait a little (1 second)
ok, err = splash:runjs("$('.title.play-ball > a:first-child').click()")
assert(splash:wait(1))
-- return result as a JSON object
return {
html = splash:html(),
error = err
-- we don't need screenshot or network activity
--png = splash:png(),
--har = splash:har(),
}
end
请注意,这个JavaScript代码对我来说不适用于Splash(屏幕截图没有显示“历史记录”的内容)。
但是我在网络界面中尝试了以下内容,并且我收到了“历史”节目(在png屏幕截图中 - 这里有评论):
function main(splash)
-- no need to load jQuery when you use splash:select
--assert(splash:autoload("https://code.jquery.com/jquery-3.1.1.min.js"))
local url = splash.args.url
assert(splash:go(url))
assert(splash:wait(15))
local element = splash:select('.title.play-ball > a:first-child')
local bounds = element:bounds()
assert(element:mouse_click{x=bounds.width/2, y=bounds.height/2})
assert(splash:wait(5))
-- return result as a JSON object
return {
html = splash:html(),
-- we don't need screenshot or network activity
--png = splash:png(),
--har = splash:har(),
}
end
确实,Splash 2.3有这种交互的助手(例如点击一个元素)。例如,请参阅splash:select和element:mouse_click
另请注意,我增加了wait()
值。
答案 1 :(得分:0)
你需要&#34;引用&#34;将脚本传递给Splash之前的脚本:
script = """Your script"""
from urllib.parse import quote
script = quote(script)
# 'Your%20script'