NoSuchElementException: Message: no such element: Unable to locate element
最初的源代码import refrom selenium import webdriverimport timebrowser = webdriver.Chrome()url = 'http://www.sse.com.cn//disclosure/credibility/supervision/inquiries/'browser.get(url)time.sleep(3) #这里必须加3秒的延
·
- 最初的源代码
import re
from selenium import webdriver
import time
browser = webdriver.Chrome()
url = 'http://www.sse.com.cn//disclosure/credibility/supervision/inquiries/'
browser.get(url)
time.sleep(3) #这里必须加3秒的延迟,因为需要等待网页加载完毕
data = browser.page_source
#print(data)
import pandas as pd
table_all = pd.DataFrame()
for i in range(10): #爬取前10页的表格
browser.find_element_by_xpath('//*[@id="ht_codeinput"]').send_keys(i + 1)
browser.find_element_by_xpath('//*[@id="pagebutton"]').click()
time.sleep(3) #这里必须加3秒的延迟,因为需要等待网页加载完毕
data = browser.page_source
p_href = '<td><a href="(.*?)" target="_blank">.*?</a></td>' #获取每个文件的链接
href = re.findall(p_href,data)
table = pd.read_html(data)[0] #获取表格数据
table['网址'] = href #拼接网址列
table_all = table_all.append(table) #拼接表格
table_all
- 报错如下
添加标题的xpath表达式,解决该问题
- 新增20和22行代码
import re
from selenium import webdriver
import time
browser = webdriver.Chrome()
url = 'http://www.sse.com.cn//disclosure/credibility/supervision/inquiries/'
browser.get(url)
time.sleep(3) #这里必须加3秒的延迟,因为需要等待网页加载完毕
data = browser.page_source
#print(data)
import pandas as pd
table_all = pd.DataFrame()
for i in range(10): #爬取前10页的表格
browser.find_element_by_xpath('//*[@id="ht_codeinput"]').send_keys(i + 1)
browser.find_element_by_xpath('//*[@id="pagebutton"]').click()
time.sleep(3) #这里必须加3秒的延迟,因为需要等待网页加载完毕
data = browser.page_source
p_title = '<td><a href=".*?" target="_blank">(.*?)</a></td>'
p_href = '<td><a href="(.*?)" target="_blank">.*?</a></td>' #获取每个文件的链接
title = re.findall(p_title,data)
href = re.findall(p_href,data)
table = pd.read_html(data)[0] #获取表格数据
table['网址'] = href #拼接网址列
table_all = table_all.append(table) #拼接表格
table_all
更多推荐
已为社区贡献2条内容
所有评论(0)