|
|
@ -10,4 +10,15 @@ response.encoding = 'utf-8'
|
|
|
|
html = response.text
|
|
|
|
html = response.text
|
|
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
|
|
ans = soup.select('div.rich_media > div.rich_media_inner ')
|
|
|
|
ans = soup.select('div.rich_media > div.rich_media_inner ')
|
|
|
|
ans1 = ans[0].text.encode()
|
|
|
|
ans1 = ans[0].text.encode()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def openreadtxt(file_name):
|
|
|
|
|
|
|
|
data = []
|
|
|
|
|
|
|
|
file = open(file_name, 'r', encoding='utf-8') # 打开文件
|
|
|
|
|
|
|
|
file_data = file.readlines() # 读取所有行
|
|
|
|
|
|
|
|
for row in file_data:
|
|
|
|
|
|
|
|
tmp_list = row.split(' ') # 按‘,’切分每行的数据
|
|
|
|
|
|
|
|
tmp_list[-1] = tmp_list[-1].replace('\n', '') # 去掉换行符
|
|
|
|
|
|
|
|
data.append(tmp_list) # 将每行数据插入data中
|
|
|
|
|
|
|
|
file.close()
|
|
|
|
|
|
|
|
return data
|