第 0008 题:一个HTML文件,找出里面的正文。
第 0009 题:一个HTML文件,找出里面的链接。
import requests
from bs4 import BeautifulSoup
def get_content(page_url):
web_data = requests.get(page_url)
soup = BeautifulSoup(web_data.content, 'lxml')
contents = soup.select('div.show-content')
result = ''
for content in contents:
result += content.get_text()
print(result)
return result
def get_href(page_url):
web_data = requests.get(page_url)
soup = BeautifulSoup(web_data.content, 'lxml')
a_tags = soup.find_all('a')
href_list = []
for a_tag in a_tags:
href = a_tag.get('href')
if href:
print(a_tag.get('href'))
href_list.append(href)
print(href_list)
return href_list
page_url = 'http://www.jianshu.com/p/40fc848414ea'
get_href(page_url=page_url)
网友评论