get方式得到網頁的資訊
#coding=utf-8
#pip install requests
#直接get到網頁的資訊
import requests
from bs4 import BeautifulSoup
response = requests.get('https://www.sogou.com/web?query=搞基建')
print(response.text) #列印搜尋出來的全部資訊
#從 response.text 找出 <div class = 'wrwrap> </div>
soup = BeautifulSoup(response.text,'html.parser')
new_list = soup.find_all(name='div',class_='vrwrap')
print(new_list)
#可以繼續從 <div class = 'wrwrap> </div> 繼續查詢
1.錯誤程式碼
Traceback (most recent call last):
File "D:/PycharmProjects/爬蟲/day1/s1.py", line 12, in <module>
print(new_list)
UnicodeEncodeError: 'gbk' codec can't encode character '\xa0' in position 2490: illegal multibyte sequence
2.編碼格式不對
3.全部改為utf-8
4.執行成功