#-*-?coding?=?utf-8?-*-
#@Time?:?2020/12/16?14:37
#@Author?:?wy
#@File?:?spider.py
#@Software?:?PyCharm

‘‘‘
實現思路
1.頁面分析，找到頁面的url，找到數據的位置
2.數據抓取，通過request庫的get請求拿到html源碼
3.數據解析，通過lxml庫的xpath語法提取所需要的數據
4.數據存儲，使用with?open將數據進行寫入
‘‘‘

#引入第三方庫，需要安裝

import?requests????????????????#數據抓取庫
from?lxml?import?etree?????????#數據解析庫
import?time????????????????????#內置函數，時間庫

#時間格式化
today?=?time.strftime（
????‘%Y{y}%m{m}%dhwpimomelus‘time.localtime（））.format（y=‘年‘m=‘月‘d=‘日‘）
print（today）

#數據抓取
url?=?“https://s.weibo.com/top/summary?cate=realtimehot“?????#熱搜地址
headers?={
“User-Agent“:?“Mozilla/5.0?（Windows?NT?10.0;?Win64;?x64）?AppleWebKit/537.36?（KHTML?like?Gecko）?Chrome/87.0.4280.88?Safari/537.36?Edg/87.0.664.60“

}????????#headers偽裝頭
response?=?requests.get（urlheaders=headers）????????#發送請求
#print（response.text）????#獲取html源碼

#數據解析
html?=?etree.HTML（response.text）??????#類型轉換

#先找到上一級標簽，然后在下面進行多次提取，使用for循環
datas?=?html.xpath（‘//*[@id=“pl_top_realtimehot“]/table/tbody/tr‘）???????#由一定的路徑
for?data?in?datas:????#循環多次提取
????data_title?=?‘‘.join（data.xpath（‘td[2]/a/text（）‘））?????#熱搜標題
????data_rank?=?‘‘.join（data.xpath（‘td[1]/text（）‘））????????#熱搜排名
????data_num?=?‘‘.join（data.xpath（‘td[2]/span/text（）‘））
????print（data_rankdata_titledata_num）

????#數據存儲，文件名是當天的日期
????with?open（“./20201228‘.txt‘“‘a‘encoding=‘utf-8‘）as?f:
????????f.write（“%s\t%s%s\n“%（data_rankdata_titledata_num））

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件????????184??2020-12-16?14:39??weibo\.idea\.gitignore

?????文件????????174??2020-12-16?14:39??weibo\.idea\inspectionProfiles\profiles_settings.xml

?????文件????????410??2020-12-16?14:39??weibo\.idea\inspectionProfiles\Project_Default.xml

?????文件????????302??2020-12-16?14:39??weibo\.idea\misc.xml

?????文件????????269??2020-12-16?14:39??weibo\.idea\modules.xml

?????文件????????361??2020-12-16?14:39??weibo\.idea\weibo.iml

?????文件???????6060??2020-12-28?23:33??weibo\.idea\workspace.xml

?????文件???????1870??2020-12-28?23:33??weibo\20201228‘.txt‘

?????文件???????1819??2020-12-28?23:33??weibo\spider.py

?????文件???????2176??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\AUTHORS

?????文件???????1315??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\COPYING.txt

?????文件??????????4??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\INSTALLER

?????文件???????1447??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\LICENSE

?????文件???????4190??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\metaDATA

?????文件???????3121??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\RECORD

?????文件??????????0??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\REQUESTED

?????文件??????????4??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\top_level.txt

?????文件?????????92??2020-12-16?14:58??weibo\venv\Lib\site-packages\beautifulsoup4-4.9.3.dist-info\WHEEL

?????文件??????18748??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\builder\_html5lib.py

?????文件??????18405??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\builder\_htmlparser.py

?????文件??????12234??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\builder\_lxml.py

?????文件??????19777??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\builder\__init__.py

?????文件??????12476??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\builder\__pycache__\_html5lib.cpython-39.pyc

?????文件??????12968??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\builder\__pycache__\_htmlparser.cpython-39.pyc

?????文件???????9418??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\builder\__pycache__\_lxml.cpython-39.pyc

?????文件??????15293??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\builder\__pycache__\__init__.cpython-39.pyc

?????文件??????34130??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\dammit.py

?????文件???????7755??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\diagnose.py

?????文件??????81650??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\element.py

?????文件???????5654??2020-12-16?14:58??weibo\venv\Lib\site-packages\bs4\formatter.py

............此處省略1722個文件信息