Last active
August 29, 2015 14:18
-
-
Save zhkuo24/1f817d31b4675bad4be5 to your computer and use it in GitHub Desktop.
获取天气预报信息
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding utf-8 -*- | |
# 获取天气预报信息 | |
import urllib.request as request | |
import re | |
import pdb | |
def gethtml(url): | |
html = request.urlopen(url).read().decode() | |
return html | |
def getweather(html): | |
try: | |
weatherlist1 = re.compile(r'<a title="(.+?)天气预报"').findall(html) | |
weatherlist2 = re.compile(r'target="_blank"><img alt="(.+?)"').findall(html) | |
weatherlist3 = re.compile(r'target="_blank"><span>(.+?)</span></a>/<a ').findall(html) | |
weatherlist4 = re.compile(r'target="_blank"><b>(.+?)</b').findall(html) | |
#time=re.compile(r'span="4">(.+?)的预报<').findall(html) | |
time=re.compile(r'城市预报列表(.+?)<span>').findall(html) | |
pdb.set_trace() | |
print(time[0]) | |
for i in (range(0,len(weatherlist1))): | |
print(weatherlist1[i],' ',weatherlist2[i],' ',weatherlist3[i],'/',weatherlist4[i]) | |
except: | |
print('获取失败,请重试!') | |
url = "http://sc.weather.com.cn/index.shtml" | |
a = gethtml(url) | |
a = getweather(a) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment