主要用到requests和bf4兩個(gè)庫(kù)將獲得的信息保存在d://hotsearch.txt下importrequests;importbs4mylist=[]r=requests.get(ur...
主要用到requests和bf4兩個(gè)庫(kù)
將獲得的信息保存在d://hotsearch.txt下
import?requests;
import?bs4
mylist=[]
r?=?requests.get(url='https://s.weibo.com/top/summary?Refer=top_hot&topnav=1&wvr=6',timeout=10)
print(r.status_code)?# 獲取返回狀態(tài)
r.encoding=r.apparent_encoding
demo?=?r.text
from?bs4?import?BeautifulSoup
soup?=?BeautifulSoup(demo,"html.parser")
for?link?in?soup.find('tbody')?:
hotnumber=''
if?isinstance(link,bs4.element.Tag):
# print(link('td'))
lis=link('td')
hotrank=lis[1]('a')[0].string#熱搜排名
hotname=lis[1].find('span')#熱搜名稱
if?isinstance(hotname,bs4.element.Tag):
hotnumber=hotname.string#熱搜指數(shù)
pass
mylist.append([lis[0].string,hotrank,hotnumber,lis[2].string])
f=open("d://hotsearch.txt","w+")
for?line?in?mylist:
f.write('%s %s %s %s\n'%(line[0],line[1],line[2],line[3]))
知識(shí)點(diǎn)擴(kuò)展：利用python爬取微博熱搜并進(jìn)行數(shù)據(jù)分析
爬取微博熱搜
import?schedule
import?pandas?as?pd
from?datetime?import?datetime
import?requests
from?bs4?import?BeautifulSoup
?
url?=?"https://s.weibo.com/top/summary?cate=realtimehot&sudaref=s.weibo.com&display=0&retcode=6102"
get_info_dict?=?{}
count?=?0
?
def?main():
global?url,?get_info_dict,?count
get_info_list?=?[]
print("正在爬取數(shù)據(jù)~~~")
html?=?requests.get(url).text
soup?=?BeautifulSoup(html,?'lxml')
for?tr?in?soup.find_all(name='tr',?class_=''):
get_info?=?get_info_dict.copy()
get_info['title']?=?tr.find(class_='td-02').find(name='a').text
try:
get_info['num']?=?eval(tr.find(class_='td-02').find(name='span').text)
except?AttributeError:
get_info['num']?=?None
get_info['time']?=?datetime.now().strftime("%Y/%m/%d %H:%M")
get_info_list.append(get_info)
get_info_list?=?get_info_list[1:16]
df?=?pd.DataFrame(get_info_list)
if?count?==?0:
df.to_csv('datas.csv',?mode='a+',?index=False,?encoding='gbk')
count?+=?1
else:
df.to_csv('datas.csv',?mode='a+',?index=False,?header=False,?encoding='gbk')
?
# 定時(shí)爬蟲(chóng)
schedule.every(1).minutes.do(main)
?
while?True:
schedule.run_pending()
pyecharts數(shù)據(jù)分析
import?pandas?as?pd
from?pyecharts?import?options?as?opts
from?pyecharts.charts?import?Bar,?Timeline,?Grid
from?pyecharts.globals?import?ThemeType,?CurrentConfig
?
df?=?pd.read_csv('datas.csv',?encoding='gbk')
print(df)
t?=?Timeline(init_opts=opts.InitOpts(theme=ThemeType.MACARONS))?# 定制主題
for?i?in?range(int(df.shape[0]/15)):
bar?=?(
Bar()
.add_xaxis(list(df['title'][i*15:?i*15+15][::-1]))?# x軸數(shù)據(jù)
.add_yaxis('num',?list(df['num'][i*15:?i*15+15][::-1]))?# y軸數(shù)據(jù)
.reversal_axis()?# 翻轉(zhuǎn)
.set_global_opts(?# 全局配置項(xiàng)
title_opts=opts.TitleOpts(?# 標(biāo)題配置項(xiàng)
title=f"{list(df['time'])[i * 15]}",
pos_right="5%",?pos_bottom="15%",
title_textstyle_opts=opts.TextStyleOpts(
font_family='KaiTi',?font_size=24,?color='#FF1493'
)
),
xaxis_opts=opts.AxisOpts(?# x軸配置項(xiàng)
splitline_opts=opts.SplitLineOpts(is_show=True),
),
yaxis_opts=opts.AxisOpts(?# y軸配置項(xiàng)
splitline_opts=opts.SplitLineOpts(is_show=True),
axislabel_opts=opts.LabelOpts(color='#DC143C')
)
)
.set_series_opts(?# 系列配置項(xiàng)
label_opts=opts.LabelOpts(?# 標(biāo)簽配置
position="right",?color='#9400D3')
)
)
grid?=?(
Grid()
.add(bar,?grid_opts=opts.GridOpts(pos_left="24%"))
)
t.add(grid,?"")
t.add_schema(
play_interval=1000,?# 輪播速度
is_timeline_show=False,?# 是否顯示 timeline 組件
is_auto_play=True,?# 是否自動(dòng)播放
)
?
t.render('時(shí)間輪播圖.html')
到此這篇關(guān)于如何用python爬取微博熱搜數(shù)據(jù)并保存的文章就介紹到這了！
掃下方二維碼加老師微信
或是搜索老師微信號(hào)：XTUOL1988【切記備注：學(xué)習(xí)Python】
領(lǐng)取Python web開(kāi)發(fā)，Python爬蟲(chóng)，Python數(shù)據(jù)分析，人工智能等學(xué)習(xí)教程。帶你從零基礎(chǔ)系統(tǒng)性的學(xué)好Python！
也可以加老師建的Python技術(shù)學(xué)習(xí)教程qq裙：245345507，二者加一個(gè)就可以！
歡迎大家點(diǎn)贊，留言，轉(zhuǎn)發(fā)，轉(zhuǎn)載，感謝大家的相伴與支持
萬(wàn)水千山總是情，點(diǎn)個(gè)【在看】行不行
*聲明：本文于網(wǎng)絡(luò)整理，版權(quán)歸原作者所有，如來(lái)源信息有誤或侵犯權(quán)益，請(qǐng)聯(lián)系我們刪除或授權(quán)事宜
