网络爬虫数据处理

1. import requests
   from bs4 import BeautifulSoup
   import pandas as pd

为解决的问题，循环没起作用

data = []
wb_data = requests.get('http://www.kugou.com/yy/rank/home/1-8888.html')
soup = BeautifulSoup(wb_data.text,'lxml')
ranks = soup.select('span.pc_temp_num')
titles = soup.select('div.pc_temp_songlist li')
times = soup.select('span.pc_temp_tips_r>span')
for rank,title,time in zip(ranks,titles,times):
    a = {
        'rank':rank.get_text().strip(),
        'singer':title.get_text().split('-')[0].split('\n')[-1],
        'song':title.get_text().split('-')[1].split('\n')[0],
        'time':time.get_text().strip()
    } 
    data.append(a) 
data

3. from pandas import DataFrame
   df = DataFrame(data)
   data

4. import pymysql
   import pandas as pd
   from pandas import DataFrame
   from pandas import Series

5. 数据库手动更改编码格式

conn = pymysql.connect(
    host = 'localhost',
    user = 'root',
    password = '986532aa',
    db = 'pystudy',
    port = 3306,
    charset = 'utf8'
)
cursor= conn.cursor()
rows = cursor.execute('select * from ch4ex9')
rows

cursor = conn.cursor()
creat = '''
    CREATE TABLE text3(
        rank int,
        singer char(8),
        song char(8),
        time char(8)
    )engine innodb default charset = utf8;'''
cursor.execute(creat)
conn.commit()

df.to_sql(name='text3',con= 'mysql+pymysql://root:986532aa@localhost:3306/pystudy?charset=utf8',if_exists='replace',index=False)