BeautifulSoup解析本地文件

 

 

import requests
from bs4 import BeautifulSoup

apex_class = ''
apex_trigger = ''
custome_object = ''
profile = ''
others = ''
path = '/Users/aaa/Downloads/aaa.htm'
htmlfile = open(path, 'r')

htmlhandle = htmlfile.read()
soup = BeautifulSoup(htmlhandle, "lxml")
#soup = BeautifulSoup(htmlhandle, "html.parser")

titles = soup.find_all("a", class_="link-gray-dark")
for title in titles:
    if 'src' in title.text:
        if '.cls' in title.text:
            apex_class += '\n'+title.text
        elif '.trigger' in title.text:
            apex_trigger += '\n'+title.text
        elif '.object' in title.text:
            custome_object += '\n'+title.text
        elif '.profile' in title.text:
            profile += '\n'+title.text
        else:
            others += '\n'+title.text
            
print ('apex_class:\n'+apex_class);
print ('apex_trigger:\n'+apex_trigger);
print ('custome_object:\n'+custome_object);
print ('profile:\n'+profile);
print ('others:\n'+others);

 

你可能感兴趣的:(爬虫)