请问如何能把news_detail4也一起进行比较？

测试积点老人 · 发表于 2020-5-22 13:59:43

python的返回值news_detail4无法被get_equal_rate_1认定为字符串，请问如何能把news_detail4也一起进行比较？
我这里是先获取新闻网页内容，然后进行比较，前三个爬取返回值可以进行比较，第四个不行，请问该怎么办？

<p>import difflib
from xml.etree.ElementTree import tostring
import requests
from lxml import etree
import time
from gne import GeneralNewsExtractor
from selenium.webdriver import Chrome
from selenium.webdriver.chrome.options import Options
def get_chinanew_data():
cookies = {
'Hm_lvt_0da10fbf73cda14a786cd75b91f6beab': '1587367903',
'Hm_lpvt_0da10fbf73cda14a786cd75b91f6beab': '1587375545',
}
headers = {
'Connection': 'keep-alive',
'Cache-Control': 'max-age=0',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'Accept-Language': 'zh-CN,zh;q=0.9',
}</p><p>response = requests.get('http://www.chinanews.com/gn/2020/04-20/9162019.shtml', headers=headers, cookies=cookies,
verify=False)
html = response.content.decode(errors='ignore')
etree_html = etree.HTML(html)
main = etree_html.xpath('//div[@id="cont_1_1_2"]')[0]
title = main.xpath('./h1/text()')[0]
pub_time = main.xpath(".//div[3]/div[@class='left-t']/text()")[0]
author = main.xpath('./div[5]/div[2]/div/span/text()')[0][:-2].split(':')[1]
pubtime = pub_time.split()[0] + ' ' + pub_time.split()[1]
content = ''.join(main.xpath('./div[@class="left_zw"]/p/text()')).strip()
site_url = 'http://www.chinanews.com/gn/2020/04-20/9162019.shtml'
site_name = '中国新闻网'
news_detail = {
'pub_time': pubtime.replace('年', '-').replace('月', '-').replace('日', ''),
'author': author,
'title': title,
'content': content.replace('\u3000', ''),
'site_url': site_url,
'site_name': site_name,
}
return news_detail
def selenium_download_data():
options = Options()
options.add_argument('--headless')
driver = Chrome(options=options,executable_path=r"C:\Users\常乐添\AppData\Local\Google\Chrome\Application\chromedriver.exe")
url_list = [
'https://news.sina.com.cn/gov/xlxw/2020-04-20/doc-iircuyvh8766402.shtml',
'https://news.ifeng.com/c/7vovtvQ2gVc',
'https://baijiahao.baidu.com/s?id=1664460259411900230&wfr=spider&for=pc']</p>