爬取湛江一周的天气状况(日期、天气状况、当天的最该最低温度)
1、爬取网站信息
def parse_url(url, headers):
# 解释url
response = requests.get(url, headers=headers)
return response.content.decode("utf-8")
2、提取有用数据
def get_weather_data(html_content):
# 提取信息 div-url-ui
metree = lxml.html.etree
# 获得解析对象
parser = metree.HTML(html_content, metree.HTMLParser())
# 使用Xpath语法获得li所有标签
li_list = parser.xpath("//div[@class='c7d']/ul[@class='t clearfix']/li")
# print(li_list)
data = []
for element in li_list:
item = {}
item["name"] = element.xpath("./h1/text()")[0]
# item["data"] = li_list[0].xpath("./h1/text()")[0]
item["weather"] = element.xpath("./p[@class='wea']/text()")[0]
item["tem_low"] = elem