21天打造分布式爬虫-中国天气网和古诗文网实战（四）

最新推荐文章于 2020-06-15 00:23:31 发布

weixin_30549175

最新推荐文章于 2020-06-15 00:23:31 发布

阅读量96

点赞数

CC 4.0 BY-SA版权

文章标签：爬虫 python

原文链接：http://www.cnblogs.com/derek1184405959/p/9403808.html

本文介绍使用Python爬虫技术抓取中国天气网的城市最低气温及古诗文网的古诗词信息，包括BeautifulSoup4和正则表达式的应用，并实现数据可视化。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

4.1.中国天气网

网址：http://www.weather.com.cn/textFC/hb.shtml

解析：BeautifulSoup4

爬取所有城市的最低天气

import requests
from bs4 import BeautifulSoup
import html5lib

def parse_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
    }
    response = requests.get(url)
    text = response.content.decode('utf-8')
    # 需要用到html5lib解析器，去补全html标签
    soup = BeautifulSoup(text,'html5lib')
    conMidtab = soup.find('div',class_='conMidtab')
    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]
            temp_td = tds[-2]
            temp = list(temp_td.stripped_strings)[0]
            print({'city':city,'temp':temp})

def main():
    url_list = [
        'http://www.weather.com.cn/textFC/hb.shtml',
        'http://www.weather.com.cn/textFC/db.shtml',
        'http://www.weather.com.cn/textFC/hd.shtml',
        'http://www.weather.com.cn/textFC/hz.shtml',
        'http://www.weather.com.cn/textFC/hn.shtml',
        'http://www.weather.com.cn/textFC/xb.shtml',
        'http://www.weather.com.cn/textFC/xn.shtml',
        'http://www.weather.com.cn/textFC/gat.shtml',
    ]
    for url in url_list:
        parse_page(url)

if __name__ == '__main__':
    main()

对爬取的数据进行可视化处理

按温度对城市进行排名
取前10个
生成直方图

代码：

import requests
from bs4 import BeautifulSoup
import html5lib
from pyecharts import Bar

ALL_DATA = []

def parse_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
    }
    response = requests.get(url)
    text = response.content.decode('utf-8')
    # 需要用到html5lib解析器，去补全html标签
    soup = BeautifulSoup(text,'html5lib')
    conMidtab = soup.find('div',class_='conMidtab')
    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]
            temp_td = tds[-2]
            temp = list(temp_td.stripped_strings)[0]
            # print({'city':city,'temp':int(temp)})
            ALL_DATA.append({'city':city,'temp':int(temp)})


def main():
    url_list = [
        'http://www.weather.com.cn/textFC/hb.shtml',
        'http://www.weather.com.cn/textFC/db.shtml',
        'http://www.weather.com.cn/textFC/hd.shtml',
        'http://www.weather.com.cn/textFC/hz.shtml',
        'http://www.weather.com.cn/textFC/hn.shtml',
        'http://www.weather.com.cn/textFC/xb.shtml',
        'http://www.weather.com.cn/textFC/xn.shtml',
        'http://www.weather.com.cn/textFC/gat.shtml',
    ]
    for url in url_list:
        parse_page(url)
    #按天气最低进行排序，并只取10个
    ALL_DATA.sort(key=lambda data:data['temp'])
    data = ALL_DATA[0:10]
    #分别取出所有城市和温度
    cities = list(map(lambda x:x['city'],data))
    temps = list(map(lambda x:x['temp'],data))

    chart = Bar("中国天气最低气温排行榜")
    chart.add('',cities,temps)
    chart.render('temperature.html')

if __name__ == '__main__':
    main()

结果：

4.2.古诗文网

网址：https://www.gushiwen.org/default_1.aspx

解析：正则表达式

代码

import requests
import re

def parse_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
    }
    response = requests.get(url,headers)
    text = response.text
    titles = re.findall(r'<div\sclass="cont">.*?<b>(.*?)</b>',text,re.DOTALL)
    dynasties = re.findall(r'<p class="source">.*?<a.*?>(.*?)</a>',text,re.DOTALL)
    authors = re.findall(r'<p class="source">.*?<a.*?>.*?<a.*?>(.*?)</a>',text,re.DOTALL)
    contents_tags = re.findall(r'<div class="contson" .*?>(.*?)</div>',text,re.DOTALL)
    contents = []
    for content in contents_tags:
        content = re.sub(r'<.*?>','',content)
        contents.append(content.strip())
    poems = []
    for value in zip(titles,dynasties,authors,contents):
        title,dynasty,author,content = value
        poem = [
            {
                'title':title,
                'dynasties':dynasty,
                'authors':author,
                'contents':content
            }
        ]
        poems.append(poem)
    for poem  in poems:
        print(poem)
        print('---'*80)

def main():
    url = 'https://www.gushiwen.org/default_1.aspx'
    for page in range(1,101):
        url = url = 'https://www.gushiwen.org/default_%s.aspx'%page
        parse_page(url)

if __name__ == '__main__':
    main()