简单的实战

0x00 获取某地七天天气预报

---

打开中国天气网，随便查询当地天气，查看返回页面的源码

发现我们需要的信息都在<ul>标签下的<li>标签中，所以这里的基本思路就是遍历<ul>标签下的<li>，每次获取日期，天气，温度三个数据，

首先定义四个函数来实现全部功能。第一个函数获取网页信息，第二个函数将信息提取存入列表，第三个函数打印这些数据，最后是一个main函数

import requests
from bs4 import BeautifulSoup

def getTHMLText(url):                                            #获取网页
    try:
        header={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:64.0) Gecko/20100101 Firefox/64.0"}  
        r = requests.get(url, headers = header)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ''

def weather_info(html, lilist):

    soup = BeautifulSoup(html, "html.parser")
    li = soup.select("ul[class='t clearfix'] li")               
    for i in li:                                                #遍历li标签，并将数据存入列表
        try:
            date = i.select("h1")[0].text                       
            wea = i.select("p[class='wea']")[0].text
            temp = i.select('p[class="tem"] span')[0].text + "/" + i.select('p[class="tem"] i')[0].text
            lilist.append([date, wea, temp])

        except:
            return ""

def printList(ulist, num):                                      #打印列表
    tplt = "{0:^10}	{1:{3}^10}	{2:^10}"
    print(tplt.format("日期", "天气", "温度", chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0], u[1], u[2], chr(12288)))


def main():
    lilist = []
    url = 'http://www.weather.com.cn/weather/101190501.shtml'
    html = getTHMLText(url)
    weather_info(html, lilist)
    printList(lilist, 7)

main()

 

0x01 单线程下载网页全部图片

---

目标网站：http://www.weather.com.cn/weather/101190501.shtml

查看源码获取思路，筛选出所有img标签，图片url是每个img标签下src的值，将其储存为列表，遍历列表下载图片

from bs4 import BeautifulSoup
import requests

def getHTMLText(url):
    try:
        header = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:64.0) Gecko/20100101 Firefox/64.0"}
        r = requests.get(url, headers=header, timeout= 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ''

def PictureUrlList(html, urls):

    soup = BeautifulSoup(html, "html.parser")
    img = soup.select('img')
    for i in img:
        try:
            src = i['src']
            urls.append(src)
        except:
            return ''


def downloader(urls):
    try:
        for u in range(len(urls)):
            header = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:64.0) Gecko/20100101 Firefox/64.0"}
            r = requests.get(urls[u], headers = header)
            pic = r.content
            path = 'D:/PIC/'+str(u)+'.png'
            with open(path, 'wb') as f:
                f.write(pic)
    except:
        pass

def main():
    urls = []
    url = "http://www.weather.com.cn/weather/101190501.shtml"
    html = getHTMLText(url)
    PictureUrlList(html, urls)
    downloader(urls)

main()