根据关键词和限制时间爬取微博信息

今天师姐要我帮她爬微博数据...

image.png
image.png
因为师姐有时间的限制
因此我们仔细观察微博的状态

发现这里有一个高级搜索
image.png
微博还是很贴心的
image.png
居然只能爬50页？？
我收回我刚才的话，哼~
然后网上发现有小哥哥写好的代码.....
copy 起来
链接丢在这里https://www.jianshu.com/p/28553c1789f9
等等好像有些地方不一样，我们改改

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# @Date    : 2020-02-28 13:32:33
# @Author  : Muxiaoxiong
# @email   : xiongweinie@foxmail.com


import time
import xlrd
import xlwt
from xlutils.copy import copy
from selenium import webdriver
from selenium.webdriver.common.keys import Keys

def write_excel_xls(path, sheet_name, value):
    index = len(value)  # 获取需要写入数据的行数
    workbook = xlwt.Workbook()  # 新建一个工作簿
    sheet = workbook.add_sheet(sheet_name)  # 在工作簿中新建一个表格
    for i in range(0, index):
        for j in range(0, len(value[i])):
            sheet.write(i, j, value[i][j])  # 像表格中写入数据（对应的行和列）
    workbook.save(path)  # 保存工作簿

def write_excel_xls_append(path, value):
    index = len(value)  # 获取需要写入数据的行数
    workbook = xlrd.open_workbook(path)  # 打开工作簿
    sheets = workbook.sheet_names()  # 获取工作簿中的所有表格
    worksheet = workbook.sheet_by_name(sheets[0])  # 获取工作簿中所有表格中的的第一个表格
    rows_old = worksheet.nrows  # 获取表格中已存在的数据的行数
    new_workbook = copy(workbook)  # 将xlrd对象拷贝转化为xlwt对象
    new_worksheet = new_workbook.get_sheet(0)  # 获取转化后工作簿中的第一个表格
    for i in range(0, index):
        for j in range(0, len(value[i])):
            new_worksheet.write(i+rows_old, j, value[i][j])  # 追加写入数据，注意是从i+rows_old行开始写入
    new_workbook.save(path)  # 保存工作簿

def read_excel_xls(path):
    workbook = xlrd.open_workbook(path)  # 打开工作簿
    sheets = workbook.sheet_names()  # 获取工作簿中的所有表格
    worksheet = workbook.sheet_by_name(sheets[0])  # 获取工作簿中所有表格中的的第一个表格
    for i in range(0, worksheet.nrows):
        for j in range(0, worksheet.ncols):
            print(worksheet.cell_value(i, j), "\t", end="")  # 逐行逐列读取数据
        print()

def spider(startime,endtime,book_name_xls,sheet_name_xls,keywords,maxWeibo):

    driver = webdriver.Chrome()
    driver.set_window_size(1400, 800)
    driver.get("https://s.weibo.com/weibo?q=%s&typeall=1&suball=1&timescope=custom:%s:%s&Refer=g&display=0&retcode=6102"%(keywords,startime,endtime))
    for i in range(60):
        time.sleep(1)
        print('进入等待时间，剩余时间为%s'%(60-i),end='\r',)
    value_title = [["rid", "用户名称", "微博内容", "微博转发量","微博评论量","微博点赞","发布时间","搜索关键词","原创or转发","文本类型"],]
    write_excel_xls(book_name_xls, sheet_name_xls, value_title)
    rid = 0
    page=0
    while rid<maxWeibo:
        page +=1
        driver.get("https://s.weibo.com/weibo?q=%s&typeall=1&suball=1&timescope=custom:%s:%s&Refer=g&page=%s"%(keywords,startime,endtime,page))
        elems=driver.find_elements_by_css_selector('div.card')
        for elem in elems:
            try:
                rid = rid + 1
                #用户名
                weibo_username = elem.find_elements_by_css_selector('a.name')[0].text
                #微博内容
                #分为有全文和无全文
                weibo_content = elem.find_elements_by_css_selector('p.txt')[0].text
                shares = elem.find_elements_by_css_selector('div.card-act > ul > li:nth-child(2)')[0].text
                shares=shares.replace("转发","")
                comments = elem.find_elements_by_css_selector('div.card-act > ul > li:nth-child(3)')[0].text
                comments=comments.replace("评论","")
                likes = elem.find_elements_by_css_selector('div.card-act > ul > li:nth-child(4)')[0].text
                try:
                    elem.find_element_by_css_selector('div[node-type="feed_list_media_prev"]')
                    content_type='文字+图片'
                except:
                    content_type='文字'
                try:
                    elem.find_element_by_css_selector('div.con')
                    yczf='转发'
                except:
                    yczf='原创'
                #发布时间
                weibo_time = elem.find_elements_by_css_selector('p.from > a:nth-child(1)')[0].text
                print("正在爬取第%s"%rid)
                value1 = [[rid, weibo_username,weibo_content, shares,comments,likes,weibo_time,keywords,yczf,content_type],]
                write_excel_xls_append(book_name_xls, value1)
            except:
                pass

if __name__ == '__main__':
    startime = "2019-09-01-0" #开始时间
    endtime = "2019-11-30-0" #结束时间
    book_name_xls = "G:/selenium+爬虫/爬取NCBI/weibo.xls" #填写你想存放excel的路径，没有文件会自动创建
    sheet_name_xls = '微博数据' #sheet表名
    maxWeibo = 20000 #设置最多多少条微博，如果未达到最大微博数量可以爬取当前已解析的微博数量
    keywords = "抑郁" #输入你想要的关键字，建议有超话的话加上##，如果结果较少，不加#
    spider(startime,endtime,book_name_xls,sheet_name_xls,keywords,maxWeibo)

又是开心的一天~