谭诗琪的作业二

代码

#第一步：打开深圳证券交易所的网页筛选深圳能源（代码000027）的财务报告，结果见图一
  from selenium import webdriver
  from selenium.webdriver.common.by import By
  from selenium.webdriver.common.keys import Keys
  # browser = webdriver.Firefox()
  browser = webdriver.Chrome()
  browser.get('https://www.szse.cn/disclosure/listed/fixed/index.html')
  # assert 'Yahoo' in browser.title
  element = browser.find_element(By.ID, 'input_code')  # Find the search box
  element.send_keys('深圳能源' + Keys.RETURN)

  element = browser.find_element(By.ID, 'disclosure-table')
  innerHTML = element.get_attribute('innerHTML')



  f = open('innerHTML.html','w',encoding='utf-8')
  f.write(innerHTML)
  f.close()



#第二步：处理和提取深圳能源的数据,结果见图二
  from bs4 import BeautifulSoup
  import re
  import pandas as pd


  def to_pretty(fhtml):
      f = open(fhtml,encoding='utf-8')
      html = f.read()
      f.close()

      soup = BeautifulSoup(html)
      html_prettified = soup.prettify()

      f = open(fhtml[0:-5]+'-prettified.html', 'w', encoding='utf-8')
      f.write(html_prettified)
      f.close()
      return(html_prettified)


  html = to_pretty('disclosure-table.html')

  def txt_to_df(html):
      # html table text to DataFrame
      p = re.compile('(.*?)', re.DOTALL)
      trs = p.findall(html)

      p2 = re.compile('(.*?)', re.DOTALL)
      tds = [p2.findall(tr) for tr in trs[1:]]

      df = pd.DataFrame({'证券代码': [td[0] for td in tds],
                         '简称': [td[1] for td in tds],
                         '公告标题': [td[2] for td in tds],
                         '公告时间': [td[3] for td in tds]})
      return(df)

  df_txt = txt_to_df(html)


  p_a = re.compile('(.*?)', re.DOTALL)
  p_span = re.compile('(.*?)', re.DOTALL)

  get_code = lambda txt: p_a.search(txt).group(1).strip()
  get_time = lambda txt: p_span.search(txt).group(1).strip()

  def get_link(txt):
      p_txt = '(.*?)'
      p = re.compile(p_txt, re.DOTALL)
      matchObj = p.search(txt)
      attachpath = matchObj.group(1).strip()
      href       = matchObj.group(2).strip()
      title      = matchObj.group(3).strip()
      return([attachpath, href, title])

  def get_data(df_txt):
      prefix = 'https://disc.szse.cn/download'
      prefix_href = 'https://www.szse.cn/'
      df = df_txt
      codes = [get_code(td) for td in df['证券代码']]
      short_names = [get_code(td) for td in df['简称']]
      ahts = [get_link(td) for td in df['公告标题']]
      times = [get_time(td) for td in df['公告时间']]
      #
      df = pd.DataFrame({'证券代码': codes,
                         '简称': short_names,
                         '公告标题': [aht[2] for aht in ahts],
                         'attachpath': [prefix + aht[0] for aht in ahts],
                         'href': [prefix_href + aht[1] for aht in ahts],
                         '公告时间': times
          })
      return(df)

  df_data = get_data(df_txt)

  df_data.to_csv('sample_data_from_szse.csv')

结果

解释

先爬取网页筛选选好的公司，再利用正则表达式和函数处理数据