信息的组织和提取

1.信息的三种类型。’

1.1  XML

2.JSON

3.YAML

三种信息的比较：

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)           # 错误表达
print(soup.find_all("a",str))                # 错误表达
print(soup.find_all(str= "Basic Python"))    # 错误表达
print(soup.find_all(string= "Basic Python")) # 正确表达   精确搜索               # ['Basic Python']
import re  
print(soup.find_all(string=re.compile("python")))   # 正则运算    模糊搜             # ['This is a python demo page', 'The demo python introduces several python courses.']

others

# 以标签属性值进行，标注属性属性检索
print(soup.find_all("p","course"))       #
print(soup.find_all(id="link1"))

print(soup.find_all(id="link"))                        # [] 只能精确搜索
print(soup.find_all(id=re.compile("link")))            # 引入正则表达式进行搜索

# 是否对子孙节点进行搜索,默认为是
print(soup.find_all("a"))
print(soup.find_all("a",recursive=False))                   # no 对子孙节点进行搜索                        # []