html_process模块

# 对包含年报信息的html文件进行处理
# 提取证券代码、证券简称、年报下载链接、年报名称以及年报发布时间
# 对dataframe进行信息筛选

import re

def html_info_sh(tr):
    '''

    解析从上交所爬取的年报html
    提取证券代码、证券简称、年报下载链接、年报名称以及年报发布时间
    
    '''
    p_td = re.compile('<td.*?>(.*?)</td>',re.DOTALL)
    tds = p_td.findall(tr)

    s = tds[0].find('>')+1
    e = tds[0].rfind('<')
    code = tds[0][s:e]

    s = tds[1].find(">")+1
    e = tds[1].rfind('<')
    name = tds[1][s:e]

    s = tds[2].find('href="')+6
    e = tds[2].find('.pdf"')+4
    href = 'http://www.sse.com.cn'+tds[2][s:e]
    
    s = tds[2].find('$(this))">')+10
    e = tds[2].find('</span>')
    title = tds[2][s:e]

    date = tds[3].strip()

    data = [code,name,href,title,date]
    return(data)

def html_info_sz(tr):
    '''

    解析从深交所爬取的年报html
    提取证券代码、证券简称、年报下载链接、年报名称以及年报发布时间
    
    '''

    # .*? 表示匹配任意数量的重复，但是在能使整个匹配成功的前提下使用最少的重复
    p_td = re.compile('<td.*?>(.*?)</td>',re.DOTALL)
    tds = p_td.findall(tr)

    s = tds[0].find('>')+1
    e = tds[0].rfind('<')
    code = tds[0][s:e]

    s = tds[1].find(">")+1
    e = tds[1].rfind('<')
    name = tds[1][s:e]

    s = tds[2].find('attachpath="')+12
    e = tds[2].find('.PDF"')+4
    href = 'https://disc.szse.cn/download'+tds[2][s:e]


    p_title = re.compile('<span.*?>(.*?)</span>',re.DOTALL)
    title = p_title.findall(tds[2])[0]


    s = tds[3].find(">")+1
    e = tds[3].rfind('<')
    date = tds[3][s:e]

    data = [code,name,href,title,date]
    return(data)

def filter(df,col,word):
    '''
    剔除df数据框中col列中包含word所在行 
    '''
    condition = df[col].to_frame().apply(lambda x:word in x[col],axis = 1)
    result = df[~condition]
    return result

def filter_mul(df,col,words):
    '''
    剔除df数据框中col列中包含words所在行 
    '''
    result = df.copy()
    for word in words:
        result = filter(result,col,word)
    return result