python爬虫新闻网页的浏览量转载量_用Python爬虫 爬博客访问量

import re

import requests

from requests import RequestException

import time

import random

def get_page(url):

try:

headers = {

'Referer': 'https://blog.csdn.net', # 伪装成从CSDN博客搜索到的文章

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'

# 伪装成浏览器

}

response = requests.get(url, headers=headers)

if response.status_code == 200:

return response.text

return None

except RequestException:

print('请求出错')

return None

def parse_page(html):

try:

read_num = int(re.compile('').search(html).group(1))

return read_num

except Exception:

print('解析出错')

return None

def main():