import requests
import re
from 朗读古诗文 import speech_convert
#数据采集
url="https://so.gushiwen.org/gushi/tangshi.aspx"
root_url="https://so.gushiwen.org"
html=requests.get(url).text
#print(html)
#提取每一个古诗的网址,re正则表达式
#result=re.findall('a=(\d)','a=1sf*a=5')
#print(result)
#\(元稹\),(元稹)括号前加上反斜杠,为了转译,不然打印不出数据(让程序忽略这个括号,告诉他括号不是特殊字符)
#poetry_url= re.findall(r"""span>a href="/shiwenv_45c396367f59.aspx" target="_blank">行宫a>\(元稹\)""",html)
#真正要截取的是(.*)部分,.*是任意字符任意长度,只做参数化不做截取
poetry_url= re.findall(r"""span>a href="(.*)" target="_blank">.*\(.*\)""",html)
#print(poetry_url)
for url in poetry_url:
#print(url)
url2=root_url+url
poetry_html =requests.get(url2).text
#选取诗歌内容
poetry_content=re.findall(r""" textarea style=.*>(.*)——(.*)《(.*)》.*>""",poetry_html)
#print(poetry_content[0])#[0]只想要第一首古诗,后面猜你喜欢不要
#提取的内容,首尾翻转一下
#reversed(poetry_content[0])
#翻转后拼接在一起
content="\n".join(reversed(poetry_content[0]))+"\n"
print(content)
#保存数据
with open('poetry.txt','a',encoding='utf-8') as f:
f.write(content)