scrapy-splash
scrapy-splash copied to clipboard
how to send cookies after authentication
Hi everyone I am having some truoble storing the cookies after the authentication. I managed to authenticate and here is a dummy user account to play with. What I want to do is after authenticating go to another part of the site by changin the url and not by clicking in it to save time.
Here is my code
class ExampleSpider(scrapy.Spider):
name = 'example'
start_urls = ["https://ident.familysearch.org/cis-web/oauth2/v3/authorization?client_secret=K7ymz%2FugczIps3SKrEjpp41QmXcDGK0BrGkSnGIunpHwQ0pq1rs%2FoAcsLaouJ0zbPaFtJ5eG7MdZ64LjiB3y5rMVFURm%2B18fjRPvje%2BeCwHiqBVqgu5i2gXzaHgaCi33ylnqSw%2F0h9uuLjo0myEJ%2FFDUhm8W9iTxDdKTonoYqbGkQ%2FwdfqPjKwLtXRjlEXq5mpkdkQZciVY4MDiSBaZJ3DfKZihyveKZSp3dC%2FJ3nH7Q%2FUjWpg8RP4fvR%2BN4ValGmrC9imWLOPlt5dwKOPsTF8z9AiOyaGOvxEn5rYzf4iNZ35Hr7X9p87BRhKvTRSuQJr24y4aPpC33EAr7QrmgZw%3D%3D&response_type=code&redirect_uri=https%3A%2F%2Fwww.familysearch.org%2Fauth%2Ffamilysearch%2Fcallback&state=%2F&client_id=3Z3L-Z4GK-J7ZS-YT3Z-Q4KY-YN66-ZX5K-176R",
"https://www.familysearch.org/search/record/results?count=20&q.anyDate.from=1500&q.anyDate.to=1650&q.anyPlace=Lima"]
def start_requests(self):
script = """
function main(splash,args)
splash:init_cookies(splash.args.cookies)
splash:set_viewport_size(1366, 768)
splash:set_user_agent('Splash bot')
local url = splash.args.url
splash:go(url)
splash:wait(5)
local form = splash: select('form[name=eventForm]')
local values = {
userName = 'abdc199',
password = 'github199',
}
assert(form:fill(values))
assert(form:submit())
assert(splash:wait(10))
return {
html=splash:html(),
cookies=splash.get_cookies()
}
end
"""
yield SplashRequest(url=self.start_urls[0],
callback=self.after_login,
session_id='1',
endpoint='execute',
args={
'lua_source': script,
'wait': 5})
def after_login(self, response):
# check login succeed before going on
if "authentication failed" in response.text:
self.logger.error("Login failed")
return
else:
url = "https://www.familysearch.org/search/record/results?count=20&q.anyDate.from=1500&q.anyDate.to=1650&q.anyPlace=Lima"
yield SplashRequest(url, self.parse_url, session_id='1', args={'wait':5})
def parse_url(self, response):
yield {
'response':response.text
}