Python网络数据抓取

import requests  #网页抓取
from bs4 import BeautifulSoup   #内容解析

import re  #正则表达式处理

#https://www.douban.com/robots.txt
r = requests.get('https://book.douban.com/subject/1986590/comments/')
#r = requests.get('https://book.douban.com/subject/1986590/comments/hot?p=4')

print(r.status_code)
#print(r.text)

#数据解析
#markup = '
The Little Prince
'
#soup = BeautifulSoup(markup, "lxml")
#print(soup.b)
#print(soup.p)
#tag = soup.p



soup = BeautifulSoup(r.text, "lxml")
pattern = soup.find_all('p','comment-content')
for item in pattern:
    print(item.string)

#re = requests.get('http://money.cnn.com/data/dow30')

pattern_s = re.compile(')


#
p = re.findall(pattern_s, r.text)
sum = 0
for star in p:
    sum += int(star)
print(sum)

---

参考资料

http://www.icourse163.org/learn/NJU-1001571005?tid=1002097008#/learn/content?type=detail&id=1002815204&cid=1003184422&replay=true