运用python采集网页信息_使用Python的BeautifulSoup 类库采集网页内容

from urllib.request importurlopenfrom bs4 importBeautifulSoup

html_doc= """

The Dormouse's story

The Dormouse's story

Once upon a time there were three little sisters; and their names were

Elsie,

Lacie and

Tillie;

and they lived at the bottom of a well.

...

...

...

"""soup= BeautifulSoup(html_doc, "html.parser")

link3= soup.find(id='link3')#Tillie

print(link3)#

print(type(link3))#{'href': 'http://example.com/tillie', 'title': 'this is title!', 'id': 'link3', 'class': ['sister', 'text-bold', 'text-danger']}

print(link3.attrs)#Tillie

print(link3.get_text())#this is title!

print(link3["title"])

all_a= soup.find_all('a')#Elsie

print(all_a[0])#['Elsie', 'Lacie', 'Tillie']

print(soup.find_all(text=["Tillie", "Elsie", "Lacie"]))#[

...

]

print(soup.find_all("p", {"class":"red", "class":"red green"}))