爬虫实践获取某城市天气数据

Posted 2022-02-19 zstar-_

功能需求

获取山东济南城市每天的天气情况。
需要获取四个数据：天气、温度、风向、风级。
url地址：http://www.weather.com.cn/weather/101120101.shtml

思路分析

该界面通过get请求，得到html数据，包含七天图示数据，故可用bs4对页面进行解析

功能一：获取今日天气

import os
import random
import time
from bs4 import BeautifulSoup
import re
import requests


# 得到网页并用bs4进行网页解析
def getHtml(url):
    # 请求头被封，于是采用多个请求头，每次随机用一个，防止被服务器识别为爬虫
    user_agent_list = [
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
        "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)"
    ]
    header = 'User-Agent': random.choice(user_agent_list)
    # 如果超时，重新进行三次连接
    reconnect = 0
    while reconnect < 3:
        try:
            with requests.get(url=url, headers=header, stream=True, timeout=20) as rep:
                # 得到中文乱码，查询网页编码方式为utf-8
                rep.encoding = 'utf-8'
                # 解析网页
                soup = BeautifulSoup(rep.text, 'html.parser')
                return soup
        except (requests.exceptions.RequestException, ValueError):
            reconnect += 1
    return []


# 获取今日天气数据
def get_content(soup):
    # 返回的是从今天开始一周7天的天气，下标[0]表示今天，如需后面几天的数据，修改下标即可
    weather = soup.findAll(name="p", attrs="class": "wea")[0].text
    weather.replace('\\\\n', '')
    # print(weather)
    # 气温同理，下标[0]表示今天最高气温/最低气温
    temperature = soup.findAll(name="p", attrs="class": "tem")[0].text
    temperature = temperature.strip()  # strip()用于剔除数据中的空格
    # print(temperature)
    # 风向同理，下标[0]表示今天风向
    wind_direction = soup.findAll(name="p", attrs="class": "win")[0].find(name="span")['title']
    # print(wind_direction)
    # 风级同理，下标[0]表示今天风级
    wind_scale = soup.findAll(name="p", attrs="class": "win")[0].find(name="i").text
    # print(wind_scale)
    return weather, temperature, wind_direction, wind_scale


if __name__ == '__main__':
    url = 'http://www.weather.com.cn/weather/101120101.shtml'
    soup = getHtml(url)
    weather, temperature, wind_direction, wind_scale = get_content(soup)
    with open(r'今日天气.txt', mode='w', encoding='utf-8') as f:
        f.write("天气：" + weather + "\\n")
        f.write("气温：" + temperature + "\\n")
        f.write("风向：" + wind_direction + "\\n")
        f.write("风级：" + wind_scale + "\\n")

功能二：获取七日天气

在功能一的基础上，利用datetime.timedelta(days=i)得到七日日期

import datetime
import os
import random

from bs4 import BeautifulSoup
import requests


# 得到网页并用bs4进行网页解析
def getHtml(url):
    # 请求头被封，于是采用多个请求头，每次随机用一个，防止被服务器识别为爬虫
    user_agent_list = [
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
        "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)"
    ]
    header = 'User-Agent': random.choice(user_agent_list)
    # 如果超时，重新进行三次连接
    reconnect = 0
    while reconnect < 3:
        try:
            with requests.get(url=url, headers=header, stream=True, timeout=20) as rep:
                # 得到中文乱码，查询网页编码方式为utf-8
                rep.encoding = 'utf-8'
                # 解析网页
                soup = BeautifulSoup(rep.text, 'html.parser')
                return soup
        except (requests.exceptions.RequestException, ValueError):
            reconnect += 1
    return []


# 获取今日天气数据
def get_content(soup, i):
    # 返回的是从今天开始一周7天的天气，下标[0]表示今天，如需后面几天的数据，修改下标即可
    weather = soup.findAll(name="p", attrs="class": "wea")[i].text
    weather.replace('\\\\n', '')
    # print(weather)
    # 气温同理，下标[0]表示今天最高气温/最低气温
    temperature = soup.findAll(name="p", attrs="class": "tem")[i].text
    temperature = temperature.strip()  # strip()用于剔除数据中的空格
    # print(temperature)
    # 风向同理，下标[0]表示今天风向
    wind_direction = soup.findAll(name="p", attrs="class": "win")[i].find(name="span")['title']
    # print(wind_direction)
    # 风级同理，下标[0]表示今天风级
    wind_scale = soup.findAll(name="p", attrs="class": "win")[i].find(name="i").text
    # print(wind_scale)
    return weather, temperature, wind_direction, wind_scale


if __name__ == '__main__':
    file = r"./天气.txt"
    path = os.getcwd()
    if os.path.exists(file):
        os.remove(file)
    url = 'http://www.weather.com.cn/weather/101120101.shtml'
    soup = getHtml(url)
    for i in range(7):
        time = datetime.date.today() + datetime.timedelta(days=i)
        weather, temperature, wind_direction, wind_scale = get_content(soup, i)
        with open(file, mode='a', encoding='utf-8') as f:
            f.write("日期: " + str(time) + "\\n")
            f.write("天气：" + weather + "\\n")
            f.write("气温：" + temperature + "\\n")
            f.write("风向：" + wind_direction + "\\n")
            f.write("风级：" + wind_scale + "\\n")
            f.write("\\n")

总体不难，比较实用，mark一下。