import requests
from bs4 import beautifulsoup
def parser_page(url):
headers =
response = requests.get(url,headers=headers)
text = response.content.decode('utf-8')
# return text
soup = beautifulsoup(text,'lxml')
conmidtab = soup.find('div',attrs=)#獲取某個標籤下的某個屬性
tables = conmidtab.find_all('table')
for table in tables:
trs = table.find_all('tr')[2:]
for tr in trs:
tds = tr.find_all('td')
city_td = tds[0]
city = list(city_td.stripped_strings)[0]#獲取值所有子孫節點文字的第乙個
temp_td = tds[-2]
min_temp = list(temp_td.stripped_strings)[0]
print(city,min_temp)
def main():
url = ''
parser_page(url)
if __name__ == '__main__':
main()
# -*- coding: utf-8 -*-
import requests
from bs4 import beautifulsoup
def parser_page(url):
headers =
response = requests.get(url,headers=headers)
text = response.content.decode('utf-8')
# return text
soup = beautifulsoup(text,'html5lib')#解析速度慢
conmidtab = soup.find('div',attrs=)#獲取某個標籤下的某個屬性
tables = conmidtab.find_all('table')
for table in tables:
trs = table.find_all('tr')[2:]
for index,tr in enumerate(trs):
tds = tr.find_all('td')
city_td = tds[0]
if index==0:
city_td = tds[1]
city = list(city_td.stripped_strings)[0]#獲取值所有子孫節點文字的第乙個
temp_td = tds[-2]
min_temp = list(temp_td.stripped_strings)[0]
print(city,min_temp)
def main():
urls = [
'','',
'','',
'','',
'','',
]# url = ''
for url in urls:
parser_page(url)
if __name__ == '__main__':
main()
# -*- coding: utf-8 -*-
import requests
from bs4 import beautifulsoup
from pyecharts import bar
all_date =
def parser_page(url):
headers =
response = requests.get(url,headers=headers)
text = response.content.decode('utf-8')
# return text
soup = beautifulsoup(text,'html5lib')#解析速度慢
conmidtab = soup.find('div',attrs=)#獲取某個標籤下的某個屬性
tables = conmidtab.find_all('table')
for table in tables:
trs = table.find_all('tr')[2:]
for index,tr in enumerate(trs):
tds = tr.find_all('td')
city_td = tds[0]
if index==0:
city_td = tds[1]
city = list(city_td.stripped_strings)[0]#獲取值所有子孫節點文字的第乙個
temp_td = tds[-2]
min_temp = list(temp_td.stripped_strings)[0]
# print()
def main():
urls = [
'','',
'','',
'','',
'','',
]# url = ''
for url in urls:
parser_page(url)
# 分析資料
# 根據最低氣溫排序
all_date.sort(key=lambda data: data['min_temp']) # date是傳遞的引數
data = all_date[:10]
# print(all_date[:10])
cities =
cities = list(map(lambda x:x['city'],data))
temps = list(map(lambda x:x['min_temp'],data))
chart = bar("中國天氣最低氣溫排行榜")
chart.add('',cities,temps)
chart.render('temperature.html')
if __name__ == '__main__':
main()
Python爬取中國天氣網天氣資料
由於一些需要,想要獲取今天的天氣資料,於是又撿起了python寫了個爬蟲用來獲取中國天氣網上的氣象資料。由於我需要的資料比較簡單,因為我只需要北京地區當天的溫度 最低溫度和最高溫度 和天氣,因此 部分比較簡單,下面就來講講這個爬取的過程。第一步 網頁分析 要進行爬蟲設計,首先得分析網頁的請求過程。首...
Python爬取中國天氣網指定城市天氣
功能 完整 import pandas as pd import requests import re 建立乙個字典儲存中國天氣網城市 def createcitycode fh r text 中國天氣網城市 csv data pd.read csv fh,engine python data da...
Python 爬取中國天氣網天氣並通過郵箱定時傳送
獲取天氣資訊指令碼如下,usr bin python3 coding utf 8 import re import requests from bs4 import beautifulsoup import io import sys r requests.get timeout 30 r.rais...