BaseDataMaintenance/BaseDataMaintenance/maintenance/2.py

import time

import gunicorn

import requests
from bs4 import BeautifulSoup

from BaseDataMaintenance.common.Utils import article_limit

import codecs

def getAttachPath(filemd5,_dochtmlcon):
    _soup = BeautifulSoup(_dochtmlcon,"lxml")

    list_mark = ["data","filelink"]
    for _mark in list_mark:
        _find = _soup.find("a",attrs={_mark:filemd5})
        filelink = ""
        if _find is None:
            _find = _soup.find("img",attrs={_mark:filemd5})
            if _find is not None:
                filelink = _find.attrs.get("src","")
        else:
            filelink = _find.attrs.get("href","")
        if filelink.find("bidizhaobiao")>=0:
            _path = filelink.split("/file")
            if len(_path)>1:
                return _path[1]

if __name__ == '__main__':

    text = codecs.open("C:\\Users\\\Administrator\\Desktop\\2.html","r",encoding="utf8").read()
    filemd5='61393b5ef3d460b3714eb9667682144f'
    print(getAttachPath(filemd5,text))