2020-2-25(93)

from bs4 import BeautifulSoup

#创建BeautifulSoup对象
r = requests.get("https://www.baidu.com")
r.encoding = "utf-8"
soup = BeautifulSoup(r.text,"html.parser")
print(soup)
print(soup.title)
print(soup.title.text)
print(type(soup.title))
print(type(soup))

#通过html文件获得BeautifulSoup对象
soup = BeautifulSoup(open("d:\\2019\\sohu\\0.html",encoding="utf-8"),"html.parser")
print(soup.title)


#格式化输出html内容
#print(soup.prettify())

#标签分析
r = requests.get("https://www.baidu.com")
r.encoding = "utf-8"
soup = BeautifulSoup(r.text,"html.parser")

print(soup.title)#第一个title标签的内容
print(soup.head)#第一个head标签的内容
print(soup.p)#第一个p标签的内容
print(soup.a) #第一个a标签的内容
print(type(soup.a))

print(soup.a.name) #第一个a标签本身名称，输出'a'
print(soup.a.attrs) #第一个a标签的所有属性
#{'href': 'http://news.baidu.com', 'name': 'tj_trnews', 'class': ['mnav']}
for k,v in soup.a.attrs.items():
    print(k,v)
print(soup.a["href"])
print(soup.a.get("href"))

soup.a["name"]="baidu_news"  #修改标签属性值
print(soup.a["name"])
print(soup.a)

del soup.a["name"]   #删除标签属性值
print(soup.a)
print(soup.a.get("name",1))

#NavigableString(标签内容)分析
print(soup.title.text)
print(soup.title.string) #第一个title标签的文本内容
print(type(soup.title.text)) #<class 'str'>
print(type(soup.title.string)) #<class 'bs4.element.NavigableString'>
soup.title.string = "百度一下，你也不知道"  #修改标签内容
print(soup.title.string)

#html结构化分析

soup = BeautifulSoup(open("d:\\2019\\sohu_html.html",encoding="utf-8"),"html.parser")
#print(soup.prettify())

#子节点
print(soup.head.contents) #head子节点的列表
print(type(soup.head.contents))  #list
#生成器方式存储子节点
l = soup.ul.children 
print(l) 
for i in l:
    print(i)

#子孙节点
for i in soup.ul.descendants:
    print(i)
    print("**************")

#节点内容及多个节点内容
print(soup.body.string) #None 包含多个节点，无法确定打印哪个节点
print(soup.title.string) #可以确定
print(soup.body.strings)
for i in soup.body.strings:
    print(i)
    print("************")

for i in soup.body.stripped_strings:  #处理了空行
    print(i)
    print("##############")


#父节点
print(soup.div.parent)
print(soup.body.parent)

content = soup.title.string
print(content)
print(content.parent)
print(content.parent.parent)
print(content.parent.parent.parent)
print("-----------------")

count=0
for i in content.parents:
    print(i.name)
    print("*****************")
    count+=1
print(count)

#兄弟节点
#next_sibling下一个，写两个是因为下一个是空格

print(soup.title.next_sibling.next_sibling) 
print((soup.title.next_sibling.next_sibling).name)
for i in soup.link.next_siblings:
    print(i)
    print("*************")

#previous_sibling上一个
print(soup.title.previous_sibling.previous_sibling) #上一个
for i in soup.title.previous_siblings:
    print(i)
    print("***************")

#前后节点
print(soup.head.next_element.next_element)
print(soup.title.previous_element.previous_element)
print("###############")

for i in soup.head.next_elements:
    print(i)
    print("***********")
    
print(soup.title.previous_elements)

#遍历文档结构查询

soup = BeautifulSoup(open("d:\\2019\\sohu_html.html",encoding="utf-8"),"html.parser")

#find_all

#字符串
print(soup.find_all("link"))

#正则
import re
for i in soup.find_all(re.compile(r'^l')):
    print(i)
    print("*************")

#传列表
print(soup.find_all(["head","body"]))