问题
I am currently trying to crawl data from three websites (three different URLs). Therefore, I am using a text-file to load the different URLs into the start_url. At the moment, there are three URLs in my file. However, the script just saves/overwrites the data of the two URLs before.
This is my code:
# -*- coding: utf-8 -*-
import scrapy
from scrapy import Spider
from selenium import webdriver
from scrapy.selector import Selector
from scrapy.http import Request
from time import sleep
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.action_chains import ActionChains
import re
import csv
class AlltipsSpider(Spider):
name = 'alltips'
allowed_domains = ['blogabet.com']
def start_requests(self):
self.driver = webdriver.Chrome('C:\webdrivers\chromedriver.exe')
with open("urls.txt", "rt") as f:
start_urls = [l.strip() for l in f.readlines()]
self.driver = webdriver.Chrome('C:\webdrivers\chromedriver.exe')
for url in start_urls:
self.driver.get(url)
self.driver.find_element_by_id('currentTab').click()
sleep(3)
self.logger.info('Sleeping for 5 sec.')
self.driver.find_element_by_xpath('//*[@id="_blog-menu"]/div[2]/div/div[2]/a[3]').click()
sleep(7)
self.logger.info('Sleeping for 7 sec.')
yield Request(self.driver.current_url, callback=self.crawltips)
def crawltips(self, response):
sel = Selector(text=self.driver.page_source)
allposts = sel.xpath('//*[@class="block media _feedPick feed-pick"]')
for post in allposts:
username = post.xpath('.//div[@class="col-sm-7 col-lg-6 no-padding"]/a/@title').extract()
publish_date = post.xpath('.//*[@class="bet-age text-muted"]/text()').extract()
yield{'Username': username,
'Publish date': publish_date
}
来源:https://stackoverflow.com/questions/58047980/selenium-scrapy-last-url-overwrites-other-urls