吴裕雄 python 爬虫

Posted 2021-01-28 天生自然

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了吴裕雄 python 爬虫相关的知识，希望对你有一定的参考价值。

import requests

from bs4 import BeautifulSoup

url = \'http://www.baidu.com\'
html = requests.get(url)
sp = BeautifulSoup(html.text, \'html.parser\')
print(sp)

html_doc = """
<html><head><title>页标题</title></head>

<p class="title"><b>文件标题</b></p>

<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
"""

from bs4 import BeautifulSoup

sp = BeautifulSoup(html_doc,\'html.parser\') 

print(sp.find(\'b\')) # 返回值：<b>文件标题</b>

print(sp.find_all(\'a\')) #返回值： [<b>文件标题</b>]

print(sp.find_all("a", {"class":"sister"}))

data1=sp.find("a", {"href":"http://example.com/elsie"})
print(data1.text) # 返回值：Elsie  

data2=sp.find("a", {"id":"link2"}) 
print(data2.text) # 返回值：Lacie

data3 = sp.select("#link3") 
print(data3[0].text) # 返回值：Tillie

print(sp.find_all([\'title\',\'a\'])) 

data1=sp.find("a", {"id":"link1"}) 
print(data1.get("href")) #返回值： http://example.com/elsie

import requests

from bs4 import BeautifulSoup

url = \'http://www.wsbookshow.com/\'
html = requests.get(url)
html.encoding="gbk"

sp=BeautifulSoup(html.text,"html.parser")
links=sp.find_all(["a","img"]) # 同时读取 <a> 和 <img>
for link in links:
    href=link.get("href") # 读取 href 属性的值
    # 判断值是否为非 None，以及是不是以http://开头
    if((href != None) and (href.startswith("http://"))): 
        print(href)

import requests

from bs4 import BeautifulSoup

url = \'http://www.taiwanlottery.com.tw/\'
html = requests.get(url)
sp = BeautifulSoup(html.text, \'html.parser\')

data1 = sp.select("#rightdown")
print(data1)

data2 = data1[0].find(\'div\', {\'class\':\'contents_box02\'})
print(data2)
print()

data3 = data2.find_all(\'div\', {\'class\':\'ball_tx\'})
print(data3)

import requests
from bs4 import BeautifulSoup

url1 = \'http://www.pm25x.com/\'  #获得主页面链接
html = requests.get(url1)  #抓取主页面数据
sp1 = BeautifulSoup(html.text, \'html.parser\')  #把抓取的数据进行解析

city = sp1.find("a",{"title":"北京PM2.5"})  #从解析结果中找出title属性值为"北京PM2.5"的标签
print(city)
citylink=city.get("href")  #从找到的标签中取href属性值
print(citylink)
url2=url1+citylink  #生成二级页面完整的链接地址
print(url2)

html2=requests.get(url2)   #抓取二级页面数据
sp2=BeautifulSoup(html2.text,"html.parser")   #二级页面数据解析
#print(sp2)
data1=sp2.select(".aqivalue")  #通过类名aqivalue抓取包含北京市pm2.5数值的标签
pm25=data1[0].text   #获取标签中的pm2.5数据
print("北京市此时的PM2.5值为："+pm25) #显示pm2.5值

import requests,os
from bs4 import BeautifulSoup
from urllib.request import urlopen

url = \'http://www.tooopen.com/img/87.aspx\'

html = requests.get(url)
html.encoding="utf-8"

sp = BeautifulSoup(html.text, \'html.parser\')

# 建立images目录保存图片
images_dir="E:\\\\images\\\\"
if not os.path.exists(images_dir):
    os.mkdir(images_dir)
    
# 取得所有 <a> 和 <img> 标签
all_links=sp.find_all([\'a\',\'img\']) 
for link in all_links:
    # 读取 src 和　href 属性内容
    src=link.get(\'src\')
    href = link.get(\'href\')
    attrs=[src,src]
    for attr in attrs:
        # 读取　.jpg 和　.png 檔
        if attr != None and (\'.jpg\' in attr or \'.png\' in attr):
            # 设置图片文件完整路径
            full_path = attr            
            filename = full_path.split(\'/\')[-1]  # 取得图片名
            ext = filename.split(\'.\')[-1]  #取得扩展名
            filename = filename.split(\'.\')[-2] #取得主文件名
            if \'jpg\' in ext: filename = filename + \'.jpg\'
            else:            filename = filename + \'.png\'
            print(attr)
            # 保存图片
            try:
                image = urlopen(full_path)
                f = open(os.path.join(images_dir,filename),\'wb\')
                f.write(image.read())
                f.close()
            except:
                print("{} 无法读取!".format(filename))

以上是关于吴裕雄 python 爬虫的主要内容，如果未能解决你的问题，请参考以下文章

吴裕雄--天生自然python编程：pycharm常用快捷键问题