【python014】Python爬取并解析潮汐天气简报-潮历数据（已更新）-CSDN博客

1.欢迎点赞、关注、批评、指正，互三走起来，小手动起来！

【python014】Python爬取并解析潮汐天气简报-潮历数据，源代码下载
【python014】Python爬取并解析潮汐天气简报-潮历数据，源代码下载
【python014】Python爬取并解析潮汐天气简报-潮历数据，源代码下载

文章目录

1.简要介绍
2.`Python`版数据爬取、解析代码

2.1 源代码
2.2 字段内容进一步解析`Python`源代码

3.参考地址

1.简要介绍

参考潮汐数据，网站地址：潮汐表快速导航，做进一步层次应用。数据可视化效果如下图所示：
发现大语言模型写的并不能解决问题，也可能是没付费的原因，haha
趁着空闲的时间撸了段代码，供已参考

2.`Python`版数据爬取、解析代码

2.1 源代码

import re
import requests
import pandas as pd
from datetime import datetime
from bs4 import BeautifulSoup 
import warnings
warnings.filterwarnings('ignore')

pd.set_option('display.width', 500)
pd.set_option('display.max_rows', 200)
pd.set_option('display.max_columns', 200)
pd.set_option('display.max_colwidth', 1000)

# 浙江-宁波市-松兰山
zj_nb_sl_url = 'https://www.eisk.cn/Calendar/1259.html'
zj_nb_sl_name = '浙江-宁波市-松兰山'
# 浙江-象山县-西泽
zj_xs_xz_url = 'https://www.eisk.cn/Calendar/463.html'
zj_xs_xz_name = '浙江-象山县-西泽'
# 浙江-象山县-石浦港
zj_xs_sp_url = 'https://www.eisk.cn/Calendar/460.html'
zj_xs_sp_name = '浙江-象山县-石浦港'

wl15tcxb = '未来15天潮汐表'

def parser_response_html( _url, _name ):
    response = requests.get( _url )  # 发送HTTP请求  
    response.raise_for_status()  # 如果请求失败，则抛出HTTPError异常  

    # 解析HTML  
    soup = BeautifulSoup(response.text, 'html.parser')
    og_title_desc = soup.find(attrs={"property": "og:description"})['content']

    result_html = []
    for a_slice in soup.find_all('a', href = re.compile(r'/Tides/\d+\.html\?date=.*?')):
        hour = a_slice.find('div', class_='hour').text.strip()
        hour_date = parser_ymd_date( hour )

        day = a_slice.find('div', class_='day').text.strip()
        _temperature = a_slice.find('div', class_='temperature').text.strip()
        humidity = a_slice.find('div', class_='humidity').text.strip()

        temperature = a_slice.find('div', class_ = 'temperature', style = re.compile(r'color:.*?') ).text.strip()

        tide2 = ';'.join( [','.join( c.string.strip() for c in t.contents ) for t in a_slice.find_all('div', attrs={'class':'tide2'})] )

        skycon = a_slice.find('div', class_='skycon').text.strip()
        visibility = a_slice.find('div', class_='visibility').text.strip()
        dswrf = a_slice.find('div', class_='dswrf').text.strip()

        wave2 = a_slice.find('div', class_='wave2').text.strip()
        wave1 = a_slice.find('div', class_='wave1').text.strip()
        wave3 = ''
        if a_slice.find('div', class_='wave3'):
            wave3 = a_slice.find('div', class_='wave3').text.strip()

        wind2 = a_slice.find('div', class_='wind2').text.strip()
        wind1 = a_slice.find('div', class_='wind1').text.strip()
        wind3 = a_slice.find('div', class_='wind3').text.strip()

        description = ''
        for desc in a_slice.find_all('div', class_='description'):
            description += desc.text.strip().replace('\n', '').replace('\r', '').replace(' ', '')
        result_html.append( [og_title_desc, hour_date, day, _temperature, humidity, temperature, tide2, skycon, visibility, dswrf, wave2, wave1, wave3, wind2, wind1, wind3 , description] )
    result_df = pd.DataFrame( result_html )
    return result_df

zj_nb_sl_df = parser_response_html( zj_nb_sl_url, zj_nb_sl_name )
zj_xs_xz_df = parser_response_html( zj_xs_xz_url, zj_xs_xz_name )
zj_xs_sp_df = parser_response_html( zj_xs_sp_url, zj_xs_sp_name )

union_df = pd.concat( [zj_nb_sl_df, zj_xs_xz_df, zj_xs_sp_df] )

union_df.columns = [ 'title' ,'hour_date' ,'day' ,'lunar_calendar' ,
                     'humidity' ,'temperature' ,'tide2' ,'skycon' ,'visibility' ,'dswrf' ,'wave2' ,'wave1' ,
                     'wave3' ,'wind2' ,'wind1' ,'wind3 ' ,'description']

union_df.to_excel('./%s-%s-%s-%s.xlsx' % ( zj_nb_sl_name ,zj_xs_xz_name ,zj_xs_sp_name ,wl15tcxb ), index=None, encoding='utf8')

数据样例解析效果如下图所示：

2.2 字段内容进一步解析`Python`源代码

datas = pd.read_excel(r'..\XX-XXX-未来15天潮汐表.xlsx')

datas['xscxqy'] = datas.title.apply(lambda title : title.split(',')[0])
datas['zcsj'] = datas.description.apply(lambda description : description.split('退潮时间')[0])

datas2 = datas[[ 'hour_date' ,'xscxqy' ,'zcsj' ]]

result = []
for inx, rw in datas2.iterrows():
    zcsj_lis = re.findall( r'(\d+):(\d+)', rw['zcsj'] )
    for sj in range(0, len(zcsj_lis), 2):
        result.append( [rw['hour_date'], rw['xscxqy'], rw['zcsj'], 
                  '%s %02d:%02d' % ( rw['hour_date'], int(zcsj_lis[sj][0]), int(zcsj_lis[sj][1]) ), 
                  '%s %02d:%02d' % ( rw['hour_date'],int(zcsj_lis[sj+1][0]), int(zcsj_lis[sj+1][1]) )] )
        
result_df = pd.DataFrame( result )
result_df.columns = ['cxsj', 'cxqy', 'zcsj_desc', 'zcsj_ks', 'zcsj_js']
result_df['zcsj_desc'] = result_df.zcsj_desc.apply(lambda zcsj_desc : zcsj_desc.replace('?', 'N'))

result_df['zcsj_ks_sjc'] = result_df.zcsj_ks.apply(lambda zcsj_ks : ret_timestamp_bystr(zcsj_ks) )
result_df['zcsj_js_sjc'] = result_df.zcsj_js.apply(lambda zcsj_js : ret_timestamp_bystr(zcsj_js) )
result_df['cxqy2'] = 'XXX-XX市-XX县'