import requests
from bs4 import BeautifulSoup
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36'
}
place=[]
pm25=[]
def get_info(url):
res=requests.get(url,headers=headers)
soup=BeautifulSoup(res.text,'lxml')
table = soup.find_all("table")
rows = table[0].find_all("tr")
i=0
for row in rows:
if(i>0):
cols=row.find_all("td")
place.append(cols[0].text)
pm25.append(int(cols[1].text))
i+=1
for d1,d2 in zip(place,pm25):
print(d1,d2)
#print(d2)
url="http://www.pm25.in/nanjing"
get_info(url)
【Python学习】爬虫:获取表格
最新推荐文章于 2024-05-10 15:55:25 发布