1.信息的三種類型。’

1.1 XML

2.JSON

3.YAML

三種信息的比較：

2.信息的提取

import requests
r = requests.get("http://python123.io/ws/demo.html")
demo = r.text

from bs4 import BeautifulSoup
soup = BeautifulSoup(demo,"html.parser")

# Tag


# print(soup.find_all(tag))    # NO tag
for tag in soup.find_all():   

string

# string
 

# print(soup.find_all("a").string)           # 錯誤表達
print(soup.find_all("a",str))                # 錯誤表達
print(soup.find_all(str= "Basic Python"))    # 錯誤表達
print(soup.find_all(string= "Basic Python")) # 正確表達   精確搜索               # [‘Basic Python‘]
import re  
print(soup.find_all(string=re.compile("
 
python")))   # 正則運算    模糊搜             # [‘This is a python demo page‘, ‘The demo python introduces several python courses.‘]

others

# 以標簽屬性值進行，標註屬性屬性檢索
print(soup.find_all("p","course"))       #
print(soup.find_all(id="link1"))

print(soup.find_all(id="link"))                        # [] 只能精確搜索
print
 
(soup.find_all(id=re.compile("link")))            # 引入正則表達式進行搜索

# 是否對子孫節點進行搜索,默認為是
print(soup.find_all("a"))
print(soup.find_all("a",recursive=False))                   # no 對子孫節點進行搜索                        # []

信息的組織和提取