分析网站css代码,使用python从css标签中提取数据
不会分析的,请看上一篇文章,如何爬取豆瓣网的
import requests
from bs4 import BeautifulSoup
def parse_page(url):
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.6776.400 QQBrowser/10.3.2577.400'
}
response = requests.get(url,headers)
text = response.content.decode('utf-8')
# soup = BeautifulSoup(text,'lxml')
# 安装 html5lib解析: pip list (查看安装命令)
# pip install html5lib
soup = BeautifulSoup(text, 'html5lib')
conMidtab = soup.find('div',class_='conMidtab')
tables = conMidtab.find_all('table')
for table in tables:
# 获取table中所有的tr,前面两个不要,代表下标0和1不要,从下标2的元素开始获取
trs = table.find_all('tr')[2:]
# for tr in trs:
# enumerate 循环的同时,拿出下标index
for index,tr in enumerate(trs):
# 从tr标签中获取所有的td标签
tds = tr.find_all('td')
# tds列表td标签中,第一个td标签中为城市名字
city_td = tds[0]
if index == 0:
city_td = tds[1]
# stripped_strings 获取标签内的文本内容
# city_td列表中第一个内容为城市的名字
city = list(city_td.stripped_strings)[0]
# td标签中,倒数第二个为温度,拿出来
temp_td = tds[-2]
# temp_td列表中拿出温度的文本内容
temp = list(temp_td.stripped_strings)[0]
print({"city":city,"temp":temp})
print("======================")
break
def main():
urls = [
'http://www.weather.com.cn/textFC/hb.shtml',
'http://www.weather.com.cn/textFC/db.shtml',
'http://www.weather.com.cn/textFC/hn.shtml',
'http://www.weather.com.cn/textFC/hd.shtml',
'http://www.weather.com.cn/textFC/gat.shtml'
]
for url in urls:
parse_page(url)
if __name__ == '__main__':
main()
python爬虫2(天气网)
最新推荐文章于 2025-06-18 17:58:09 发布
