批处理之家 - Powered by Discuz! Board

# pip install requests # 安装爬虫模块,用来抓取网页的html源代码
# pip install beautifulsoup4 # 安装html代码解析模块
# pip install prettytable #安装PrettyTable模块，可以将输出内容如表格方式整齐地输出
import requests # 导入爬虫模块
from bs4 import BeautifulSoup # 导入html代码解析模块
from prettytable import PrettyTable # 导入整齐输出模块
url = "http://www.weather.com.cn/weather/101210101.shtml"
get_html = requests.get(url) # 获取html源代码
soure = BeautifulSoup(get_html.content,"html.parser")
body = soure.find("body") # 找到body标签
div = body.find("div",id = "7d") # 找到div开头,并且属性有"id="7d""的标签
ul = div.find("ul") # 从 div开头并且属性有"id="7d""的标签中找到ul标签
li = ul.find_all("li") # 找到所有的li标签
list=[]
for shuju in li: # 遍历标签
dic={}
riqi = shuju.find("h1").string # 找到hl标签并提取日期
dic["date"] = riqi # 把获取到的添加到字典
tianqi= shuju.find_all("p") # 找到所有的p标签
dic["tq"] = tianqi[0].string #
wendu = tianqi[1].find("span")
dic["maxwd"] = wendu.string + "℃"
wendu2= tianqi[1].find("i")
dic["minwd"] = wendu2.string
fengxiang = tianqi[2].find("span")["title"]
dic["fx"] = fengxiang
fengli = tianqi[2].find("i")
dic["fl"] = fengli.string
list.append(dic)
table = PrettyTable(["日期", "天气","最高温度","最低温度","风向","风力"])
#for i in range(0,7):
# a = list[i]["date"],list[i]["tq"], list[i]["maxwd"], list[i]["minwd"], list[i]["fx"], list[i]["fl"]
# print(a)
for i in range(0,7):
table.add_row([list[i]["date"],list[i]["tq"], list[i]["maxwd"], list[i]["minwd"], list[i]["fx"], list[i]["fl"]])
print(table)

复制代码

table = PrettyTable(["日期", "天气","最高温度","最低温度","风向","风力"])
#for i in range(0,7):
# a = list[i]["date"],list[i]["tq"], list[i]["maxwd"], list[i]["minwd"], list[i]["fx"], list[i]["fl"]
# print(a)
for i in range(0,7):
table.add_row([list[i]["date"],list[i]["tq"], list[i]["maxwd"], list[i]["minwd"], list[i]["fx"], list[i]["fl"]])
print(table)

复制代码

tabl = PrettyTable(["日期", "天气","最高温度","最低温度","风向","风力"])
templst=[list(dic.values()) for dic in lst]
for i in range(7):
tabl.add_row(templst[i])
print(tabl)

复制代码

import requests # 导入爬虫模块
from bs4 import BeautifulSoup # 导入html代码解析模块
from prettytable import PrettyTable # 导入整齐输出模块
url = "http://www.weather.com.cn/weather/101210101.shtml"
get_html = requests.get(url) # 获取html源代码
soure = BeautifulSoup(get_html.content,"html.parser")
body = soure.find("body") # 找到body标签
div = body.find("div",id = "7d") # 找到div开头,并且属性有"id="7d""的标签
ul = div.find("ul") # 从 div开头并且属性有"id="7d""的标签中找到ul标签
li = ul.find_all("li") # 找到所有的li标签
lst = [[i.find("h1").string,
i.find_all("p")[0].string,
i.find_all("p")[1].find("span").string+"℃",
i.find_all("p")[1].find("i").string,
i.find_all("p")[2].find("span")["title"],
i.find_all("p")[2].find("i").string] for i in li]
table = PrettyTable(["日期", "天气","最高温度","最低温度","风向","风力"])
for i in range(7):
table.add_row(lst[i])
print(table)

复制代码