pandas分割字符串
requtes爬取天气后获取如下图dataframe，要求将【b】列中数据分割成【天气，最高温度，最低温度】三列。import bs4
import requests
import numpy as np
import pandas as pd
url = 'http://m.apporid.com/xian/1yue.html'
headers = {'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, '
'like Gecko) Chrome/91.0.4472.164 Mobile Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,'
'*/*;q=0.8,application/signed-exchange;v=b3;q=0.9 ',
}
res = requests.get(url, headers=headers)
temperature = []
soup = bs4.BeautifulSoup(res.text, "html.parser")
targets = soup.find("ul", class_="tqullist tqicon28x20")
targets = targets.find_all('li')
for each in targets:
temperature.append(each.text.split())
t1 = np.array(temperature).reshape(len(temperature), 2)
df = pd.DataFrame(t1, columns=["日期", "b"])
print(df)
图片
不要按下标索引分组方法。 df.b.str.split('/', expand=True)#通常可以。 可你这前面中文天气和低温连在了一起咋分都不方便。。看看有没有正则高手，可以帮你掰开，哈哈
话说，你直接爬取的时候，分好3列，不好些吗，比如
import bs4, requests, re
import numpy as np
import pandas as pd
url = 'http://m.apporid.com/xian/1yue.html'
res = requests.get(url,)
temperature = []
soup = bs4.BeautifulSoup(res.text, "html.parser")
targets = soup.find("ul", class_="tqullist tqicon28x20")
dt = targets.find_all('b')
tq = targets.find_all('div')
temp = targets.find_all('span')
for d, i, j in zip(dt, tq, temp):
temperature.append()
# print()
t1 = np.array(temperature).reshape(len(temperature), 3)
df = pd.DataFrame(t1, columns=["日期", "天气", "温度"])
print(df)
用正则吧
页:
[1]