【发布时间】:2020-07-02 08:36:35
【问题描述】:
我正在使用 selenium 和 Python 来抓取网站。我无法使用 Beautiful Soup 抓取特定的表格。 这是代码
from selenium import webdriver
from selenium.webdriver.support.ui import Select
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from bs4 import BeautifulSoup
import pandas as pd
from bs4 import BeautifulSoup
from selenium.webdriver.support import expected_conditions
link='http://omms.nic.in/#'
browser=webdriver.Firefox()
browser.get(link)
time.sleep(15)
WebDriverWait(browser, 10).until(EC.element_to_be_clickable((By.XPATH, '/html/body/div[1]/div/div/ul/li[3]/a'))).click()
time.sleep(10)
WebDriverWait(browser, 10).until(EC.element_to_be_clickable((By.XPATH, '/html/body/div[1]/div/div/ul/li[3]/ul/li[1]/ul/li[5]/a'))).click()
select_state=Select(browser.find_element_by_xpath('/html/body/div[2]/div[1]/form/table/tbody/tr[1]/td[3]/select'))
select_state.select_by_index(35)
WebDriverWait(browser, 10).until(EC.element_to_be_clickable((By.XPATH, '/html/body/div[2]/div[1]/form/table/tbody/tr[3]/td[7]/input[1]'))).click()
select_district=Select(browser.find_element_by_xpath('/html/body/div[2]/div[1]/form/table/tbody/tr[1]/td[5]/select'))
options = [x.text for x in select_district.options]
select_district.select_by_index(3)
select_year=Select(browser.find_element_by_xpath('/html/body/div[2]/div[1]/form/table/tbody/tr[2]/td[3]/select'))
select_year.select_by_index(8)
time.sleep(10)
WebDriverWait(browser, 10).until(EC.element_to_be_clickable((By.XPATH, '/html/body/div[2]/div[1]/form/table/tbody/tr[4]/td[3]/input'))).click()
time.sleep(5)
soup=BeautifulSoup(browser.page_source,"html.parser")
table=soup.find_all('table',attrs={'class':"A35402edea1d24691942da96210fa88a3382"})
data_name = pd.read_html(str(table))[0]
我收到错误,因为找不到表
【问题讨论】:
标签: python html selenium beautifulsoup