我遇到了我的 Lua 脚本拒绝执行的问题。从 ScrapyRequest 调用返回的响应似乎是一个 HTML 正文,而我期待一个文档标题。我假设 Lua 脚本从未被调用,因为它似乎对响应没有明显影响。我已经通过文档挖掘了很多,似乎无法弄清楚这里缺少什么。有没有人有什么建议?
from urlparse import urljoin
import scrapy
from scrapy_splash import SplashRequest
GOOGLE_BASE_URL = 'https://www.google.com/'
GOOGLE_QUERY_PARAMETERS = '#q={query}'
GOOGLE_SEARCH_URL = urljoin(GOOGLE_BASE_URL, GOOGLE_QUERY_PARAMETERS)
GOOGLE_SEARCH_QUERY = 'example search query'
LUA_SCRIPT = """
function main(splash)
assert(splash:go(splash.args.url))
return splash:evaljs("document.title")
end
"""
SCRAPY_CRAWLER_NAME = 'google_crawler'
SCRAPY_SPLASH_ENDPOINT = 'render.html'
SCRAPY_ARGS = {
'lua_source': LUA_SCRIPT
}
def get_search_url(query):
return GOOGLE_SEARCH_URL.format(query=query)
class GoogleCrawler(scrapy.Spider):
name=SCRAPY_CRAWLER_NAME
search_url = get_search_url(GOOGLE_SEARCH_QUERY)
def start_requests(self):
response = SplashRequest(self.search_url,
self.parse, endpoint=SPLASH_ENDPOINT, args=SCRAPY_ARGS)
yield response
def parse(self, response):
doc_title = response.body_as_unicode()
print doc_title