代码效果演示
Gitee源码
# -*- coding: utf-8 -*-
# Version: Python 3.9.7
# Author: TRIX
# Date: 2021-10-04 17:36:05
# Use:抓取今日头条微博相关部分信息 并将信息储存到txt headers储存到json
from urllib.parse import urlencode
import requests
import pyperclip,json
from dateutil.parser import parse#处理时间
def getHeaders(noKeys=None,extraStripChars=[':'],doPrint=False,):
'''noKeys 根据键名去除键值对 键名与键名间以一个space分割 忽略大小写 忽略是否strip
extraStripChars 额外strip键名的无关字符 字符与字符间以一个space分割
doPrint 是否打印headers和去除的键值对 只有在初次创建headers.json有用'''
strs=pyperclip.paste()#读取剪贴字符串
headers={}
if 'Mozilla' not in strs:#如果复制字符串不是请求标头
try:
with open('headers.json','r',encoding='utf-8') as f:#读取储存的headers
headers=json.loads(f.read())#json文本转dict对象
except FileNotFoundError:
return print('请至少完整复制一次请求标头信息\n复制方法：f12-网络-f5-名称-任意一个条目-标头-请求标头-复制所有')
if not headers:
def stripChars(word):#strip键名的无关字符
word=word.strip()
for char in extraStripChars:
word=word.strip(char)
return word
keysValues=[]
for keyOrValue in strs.split(': '):#以: 和\n切分字符串
for kOrV in keyOrValue.split('\r\n'):
keysValues.append(stripChars(kOrV))
for i in range(0,len(keysValues),2):#生成headers字典
headers[keysValues[i]]=keysValues[i+1]
if noKeys:#去除指定键值对
popKvs=[]
for key in noKeys.split():
popKvs.append(f"'{key}':'{headers.pop(stripChars(key))}'")
json_data=json.dumps(headers,ensure_ascii=False,indent=2)#dict对象转json文本 ensure_ascii让输出结果是中文而不是unicode indent缩进字符个数 值只能是 dict list int float str bool None
with open('headers.json','w',encoding='utf-8') as h:#储存json数据
h.write(json_data)
print('headers信息已储存至headers.json')
if doPrint:#打印
print('headers={')
for k,v in headers.items():
print(f"'{k}':'{v}',")
print('}')
if popKvs:
print('\n去除headers的键值对如下：')
for kv in popKvs:
print(kv)
print('\n')
return headers
def getPage(page):
params={
'uid':1618051664,
'page':page,#通过page刷新微博
'feature':0,
}
url='https://weibo.com/ajax/statuses/mymblog?'+urlencode(params)#构造url
try:
response=requests.get(url,headers=headers,)#请求数据
print(f'正在尝试爬取数据：{url}响应码：{response.status_code}')
if response.status_code==200:
return response.json()
except requests.ConnectionError as e:
print('爬取失败：',e.args)
def getLongText(urlid):
url='https://weibo.com/ajax/statuses/longtext?id='+urlid#构造url
try:
response=requests.get(url,headers=headers,)#请求数据
print(f'检测到长文本 正在尝试爬取数据：{url}，响应码：{response.status_code}')
if response.status_code==200:
return response.json()
except requests.ConnectionError as e:
print('爬取失败：',e.args)
def getblogs(json):
if json:#如果json!=None
blogs=json.get('data').get('list')
articleCount=len(blogs)
articles=[]
for blog in blogs:
#print(blog)
info={}#微博数据
info['id']=blog.get('idstr')
info['createTime']=str(parse(blog.get('created_at'))).split('+')[0]#处理时间格式
if blog.get('isLongText'):#如果微博为长文本
longText=getLongText(blog.get('mblogid'))
if longText:
longText=longText.get('data')
info['text']=longText.get('longTextContent')
topicStruct=longText.get('topic_struct')
if topicStruct:
info['topics']=''
for topic in topicStruct:
info['topics']+=topic.get('topic_title')+' '
else:
info['topic']='无'
else:
info['text']=blog.get('text_raw')
if blog.get('retweeted_status'):#如果微博含转载内容
info['text']+='该微博含转载微博 内容略'
if info.get('page_info'):#如果微博有视频或图片
info['text']+='该微博含视频 或 图片 内容略'
tagStruct=blog.get('tag_struct')
if tagStruct:#如果有标签
info['tags']=''
for tag in tagStruct:
info['tags']+=tag.get('tag_name')+' '
else:
info['tags']='无'
topicStruct=blog.get('topic_struct')
if topicStruct:#如果该微博有主题
info['topics']=''
for topic in topicStruct:
info['topics']+=topic.get('topic_title')+' '
else:
info['topics']='无'
info['likesCount']=blog.get('attitudes_count')
info['commentsCount']=blog.get('comments_count')
info['repostsCount']=blog.get('reposts_count')
info['text']=info['text'].strip('')#替换一些不正常字符
info['text']=info['text'].replace('>','>')
if 'http' in info['text']:#如果有视频链接
textAndUrl=info['text'].split('http')
info['text']=textAndUrl[0]
info['videoUrl']='http'+textAndUrl[-1]
else:
info['videoUrl']='无'
articles.append(info)
return articles
def getPageblogs(pages):#抓取pages页的所有微博的部分相关信息
with open('blogs.txt','w',encoding='utf-8') as f:
f.write('微博页面链接：{}\n'.format(headers['referer']))
f.write(f'共抓取了{pages}页微博相关信息，抓取信息如下：\n\n')
for n in range(pages):
json=getPage(n+1)
articles=getblogs(json)
f.write(f'---第{n+1}页---\n')
for i,a in enumerate(articles):
f.write(f'---第{i+1}个微博---\n')
f.write('微博id：{}\n'.format(a['id']))
f.write('发布时间：{}\n'.format(a['createTime']))
f.write('内容：{}\n'.format(a['text']))
f.write('视频链接：{}\n'.format(a['videoUrl']))
f.write('微博标签：{}\n'.format(a['tags']))
f.write('微博主题：{}\n'.format(a['topics']))
f.write('点赞数：{}\n'.format(a['likesCount']))
f.write('评论数：{}\n'.format(a['commentsCount']))
f.write('转载数：{}\n'.format(a['repostsCount']))
f.write('\n')
headers=getHeaders(noKeys='path')
getPageblogs(3)
