我真的开始对scrapy splash的工作方式感到沮丧。我不明白如何选择值并在选择值后截取屏幕截图。到目前为止,我的代码不起作用....
抓取网址:https://www.chewy.com/kong-classic-dog-toy-large/dp/38485
选择了大,但我想在这种情况下选择小并在之后截取屏幕截图。
import scrapy
from scrapy_splash import SplashRequest, SplashFormRequest
from scrapy import FormRequest, Selector
class QuotesSpider(scrapy.Spider):
name = "quotes"
def start_requests(self):
urls = [
'https://www.chewy.com/kong-classic-dog-toy-large/dp/38485',
]
for url in urls:
yield scrapy.Request(url=url, callback=self.parse)
# Gets HTML and saves to file
def parse(self, response):
page = response.url.split("/")[-2]
filename = 'quotes-%s.html' % page
with open(filename, 'wb') as f:
f.write(response.body)
self.log('Saved file %s' % filename)
yield FormRequest.from_response(
response,
formname='sku-selector',
formdata={
'15949': 'Small',
}
)
with open('request.png', 'wb') as f:
f.write(response.body)