详解用python写网络爬虫-爬取新浪微博评论

# -*- coding:gbk -*-
import re
import requests
import json
from lxml import html
#测试微博4054483400791767
comments=[]

def get_page(weibo_id):
  url='https://m.weibo.cn/status/{}'.format(weibo_id)
  html=requests.get(url).text
  regcount=r'"comments_count": (.*"https://m.weibo.cn/api/comments/show".format(id,page)
  response=requests.get(url)
  return response

def get_weibo_comments(response):
  json_response=json.loads(response.text)
  for i in range(0,len(json_response['data'])):
    comment=opt_comment(json_response['data'][i]['text'])
    comments.append(comment)


weibo_id=input("输入微博id，自动返回前5页评论：")
weibo_id=int(weibo_id)
print('\n')
page=get_page(weibo_id)
for page in range(1,page+1):
  response=get_responses(weibo_id,page)
  get_weibo_comments(response)

for com in comments:
  print(com)
print(len(comments))