| 76 | 2017-08-31 |
| 77 | """ |
| 78 | def get_informations(self, url): |
| 79 | req = requests.get(url = url, headers = self.headers) |
| 80 | req.encoding = 'utf-8' |
| 81 | html = req.text |
| 82 | page_bf = BeautifulSoup(html, 'lxml') |
| 83 | #股票名称，股票代码 |
| 84 | name = page_bf.find_all('span', class_ = 'name')[0].string |
| 85 | # code = page_bf.find_all('span', class_ = 'code')[0].string |
| 86 | # code = re.findall('\d+',code)[0] |
| 87 | |
| 88 | #存储各个表名的列表 |
| 89 | table_name_list = [] |
| 90 | table_date_list = [] |
| 91 | each_date_list = [] |
| 92 | url_list = [] |
| 93 | #表名和表时间 |
| 94 | table_name = page_bf.find_all('div', class_ = 'titlebar3') |
| 95 | for each_table_name in table_name: |
| 96 | #表名 |
| 97 | table_name_list.append(each_table_name.span.string) |
| 98 | #表时间 |
| 99 | for each_table_date in each_table_name.div.find_all('select', id = re.compile('.+1$')): |
| 100 | url_list.append(re.findall('(\w+)1',each_table_date.get('id'))[0]) |
| 101 | for each_date in each_table_date.find_all('option'): |
| 102 | each_date_list.append(each_date.string) |
| 103 | table_date_list.append(each_date_list) |
| 104 | each_date_list = [] |
| 105 | return name,table_name_list,table_date_list,url_list |
| 106 | |
| 107 | """ |
| 108 | 函数说明:财务报表入库 |