獲取網頁數據無非就三步！

第一步：首先通過python獲取到前端html完整代碼！（需要用到request模塊）

第二步：通過獲取到的html代碼進行過濾，獲取到有用天氣數據 （需要用到bs4模塊下的BeautifulSoup）

第三步：獲取到的天氣數據，進行本地化保存

PS：其它用到的模塊：time、random、socket、csv、http.client

廢話不多說，直接上代碼！

首先，導入引用模塊

from bs4 import BeautifulSoup
import requests, time, random, socket, csv
import http.client

第一步：首先通過python獲取到前端html完整代碼！（需要用到request模塊）

# 獲取請求網址的完整HTML代碼
def htmlcontent(url, data=None):
    header = {
        ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘,
        ‘Accept-Encoding‘: ‘gzip, deflate, sdch‘,
        ‘Accept-Language‘: ‘zh-CN,zh;q=0.8‘,
        
 
‘Connection‘: ‘keep-alive‘,
        ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.235‘
    }   # request 的請求頭
    timeout = random.choice(range(80, 180))
    while True:
        try:
            rep = requests.get(url, headers=header, timeout=timeout)   #
 
 請求url地址，獲得返回response信息
            rep.encoding = ‘utf-8‘
            break
        except socket.timeout as e:
            print(‘3:‘, e)
            time.sleep(random.choice(range(8, 15)))

        except socket.error as e:
            print(‘4:‘, e)
            time.sleep(random.choice(range(20, 60)))

        except http.client.BadStatusLine as e:
            print(‘5:‘, e)
            time.sleep(random.choice(range(30, 80)))

        except http.client.IncompleteRead as e:
            print(‘6:‘, e)
            time.sleep(random.choice(range(5, 15)))
    return rep.text   # 返回的Html全部代碼

第二步：通過獲取到的html代碼進行過濾，獲取到有用天氣數據 （需要用到bs4模塊下的BeautifulSoup）

# 過濾篩選有用數據
def weatherdata(html_text):
    data_al = []
    bs = BeautifulSoup(html_text, "html.parser")   # 創建BeautifulSoup對象並以html.parser方式解析
    li = bs.body.find(‘div‘, {‘id‘: ‘7d‘}).find(‘ul‘).find_all(‘li‘)   # 根據前端HTML代碼的標簽獲取具體天氣數據

    for data in li:
        temp = []
        date = data.find(‘h1‘).string
        inf = data.find_all(‘p‘)
        weather = inf[0].string   # 天氣
        temperature_highest = inf[1].find(‘span‘).string    # 最高溫度
        temperature_low = inf[1].find(‘i‘).string   # 最低溫度
        temp.append(date)   # 添加日期
        temp.append(weather)    # 添加天氣
        temp.append(temperature_low)    # 添加最低溫度
        temp.append(temperature_highest)    # 添加最高溫度
        data_al.append(temp)  # 數據全部儲存在一個列表中
    return data_al

第三步：獲取到的天氣數據，進行本地化保存

# 把數據寫入本地文件
def writedata(data, name):
    with open(name, ‘a‘, errors=‘ignore‘, newline=‘‘) as f:
        f_csv = csv.writer(f)
        f_csv.writerows(data)

最後，進行調用

if __name__ == ‘__main__‘:
    url = ‘http://www.weather.com.cn/weather/101010100.shtml‘   # 獲取天氣數據的網址
    html = htmlcontent(url)    # 獲取網頁信息
    result = weatherdata(html)    # 解析網頁信息，拿到需要的數據
    writedata(result, ‘C:/Users/LoveCounter/Desktop/天氣test.csv‘)  # 數據寫入到 csv文檔中

完整性代碼，如下：

from bs4 import BeautifulSoup
import requests, time, random, socket, csv
import http.client


# 獲取請求網址的完整HTML代碼
def htmlcontent(url, data=None):
    header = {
        ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘,
        ‘Accept-Encoding‘: ‘gzip, deflate, sdch‘,
        ‘Accept-Language‘: ‘zh-CN,zh;q=0.8‘,
        ‘Connection‘: ‘keep-alive‘,
        ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.235‘
    }   # request 的請求頭
    timeout = random.choice(range(80, 180))
    while True:
        try:
            rep = requests.get(url, headers=header, timeout=timeout)   # 請求url地址，獲得返回response信息
            rep.encoding = ‘utf-8‘
            break
        except socket.timeout as e:
            print(‘3:‘, e)
            time.sleep(random.choice(range(8, 15)))

        except socket.error as e:
            print(‘4:‘, e)
            time.sleep(random.choice(range(20, 60)))

        except http.client.BadStatusLine as e:
            print(‘5:‘, e)
            time.sleep(random.choice(range(30, 80)))

        except http.client.IncompleteRead as e:
            print(‘6:‘, e)
            time.sleep(random.choice(range(5, 15)))
    return rep.text   # 返回的Html全部代碼

# 過濾篩選有用數據
def weatherdata(html_text):
    data_al = []
    bs = BeautifulSoup(html_text, "html.parser")   # 創建BeautifulSoup對象並以html.parser方式解析
    li = bs.body.find(‘div‘, {‘id‘: ‘7d‘}).find(‘ul‘).find_all(‘li‘)   # 根據前端HTML代碼的標簽獲取具體天氣數據

    for data in li:
        temp = []
        date = data.find(‘h1‘).string
        inf = data.find_all(‘p‘)
        weather = inf[0].string   # 天氣
        temperature_highest = inf[1].find(‘span‘).string    # 最高溫度
        temperature_low = inf[1].find(‘i‘).string   # 最低溫度
        temp.append(date)   # 添加日期
        temp.append(weather)    # 添加天氣
        temp.append(temperature_low)    # 添加最低溫度
        temp.append(temperature_highest)    # 添加最高溫度
        data_al.append(temp)  # 數據全部儲存在一個列表中
    return data_al


# 把數據寫入本地文件
def writedata(data, name):
    with open(name, ‘a‘, errors=‘ignore‘, newline=‘‘) as f:
        f_csv = csv.writer(f)
        f_csv.writerows(data)


if __name__ == ‘__main__‘:
    url = ‘http://www.weather.com.cn/weather/101010100.shtml‘   # 獲取天氣數據的網址
    html = htmlcontent(url)    # 獲取網頁信息
    result = weatherdata(html)    # 解析網頁信息，拿到需要的數據
    writedata(result, ‘C:/Users/LoveCounter/Desktop/天氣test.csv‘)  # 數據寫入到 csv文檔中

關於如何只用python獲取網頁天氣（數據）的方法