我正在抓取一个具有 javascript 的网站以转到下一页。我正在使用 splash 在第一页上执行我的 javascript 代码。但我能够进入第二页。但我无法进入 3,4,5.... 页面。仅一页后停止爬行。
我正在抓取的链接:http: //59.180.234.21:8788/user/ viewallrecord.aspx
编码:
import scrapy
from scrapy_splash import SplashRequest
from time import sleep
class MSEDCLSpider(scrapy.Spider):
name = "msedcl_spider"
scope_path = 'body > table:nth-child(11) tr > td.content_area > table:nth-child(4) tr:not(:first-child)'
ref_no_path = "td:nth-child(1) ::text"
title_path = "td:nth-child(2) ::text"
end_date_path = "td:nth-child(5) ::text"
fee_path = "td:nth-child(6) ::text"
start_urls = ["http://59.180.234.21:8788/user/viewallrecord.aspx"]
lua_src = """function main(splash)
local url = splash.args.url
splash:go(url)
splash:wait(2.0)
splash:runjs("document.querySelectorAll('#lnkNext')[0].click()")
splash:wait(4.0)
return {
splash:html(),
}
end
"""
def start_requests(self):
for url in self.start_urls:
yield SplashRequest(
url,
self.parse,
endpoint='execute',
method='POST',
dont_filter=True,
args={
'wait': 1.0,
'lua_source': self.lua_src,
},
)
def parse(self, response):
print response.status
scopes = response.css('#page-info').extract()[0]
print(response.url)
print(scopes)
我是scrapy和splash的新手。请温柔一点。谢谢