Python爬虫01

Python爬虫

01百度

# 导入模块
from urllib import request
# 2. 准备网址
url = 'http://www.baidu.com/'
# 3. 打开链接,得到响应
res = request.urlopen(url)
# 4. 展现（print）响应结果
print(res.read())

02下载图片

from urllib import request
import requests
import bs4
# request.urlretrieve(图片链接，保存在本地的包含文件路径名称)
request.urlretrieve("http://img.netbian.com/file/2020/0904/de2f77ed1090735b441ba5e4c2b460ca.jpg","E:\Python-Work\Work01\爬虫01\images\\女孩.jpg")

03抓取百度首页信息

# 导入模块
import requests
import chardet
# 2.准备网址
url = 'https://www.baidu.com'
# 3.访问网址
res = requests.get(url)
# 获取编码
encode = chardet.detect(res.content)
print(encode)
# 4.设置编码
# res.encoding = encode.get('encoding')
res.encoding='utf-8'
# 5.展示信息
print(res.text)

04增加浏览器信息

# 导入模块
import requests
import chardet
import random
# 2.准备网址
url = 'https://www.baidu.com'
user_agent = [
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
    "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
    "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
    "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
    "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
    "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
    "UCWEB7.0.2.37/28/999",
    "NOKIA5700/ UCWEB7.0.2.37/28/999",
    "Openwave/ UCWEB7.0.2.37/28/999",
    "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
    # iPhone 6：
  "Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",

]
# 3.访问网址
res = requests.get(url,headers={'User-Agent':random.choice(user_agent)})
# 获取编码
encode = chardet.detect(res.content)
print(encode)
# 4.设置编码
res.encoding = encode.get('encoding')
# res.encoding='utf-8'
# 5.展示信息
print(res.text)

05编写函数返回访问结果

# 导入模块
import requests
import chardet
import random

def getHtml(url):
    # 2.准备网址
    user_agent = [
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
        "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
        "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
        "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
        "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
        "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
        "UCWEB7.0.2.37/28/999",
        "NOKIA5700/ UCWEB7.0.2.37/28/999",
        "Openwave/ UCWEB7.0.2.37/28/999",
        "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
        # iPhone 6：
      "Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",

    ]
    # 3.访问网址
    res = requests.get(url,headers={'User-Agent':random.choice(user_agent)})
    # 获取编码
    encode = chardet.detect(res.content)
    # 4.设置编码
    res.encoding = encode.get('encoding')
    # 5.展示信息
    return res
url='http://www.jd.com'
res=getHtml(url)

print(res.status_code)
print(res.text)

正则表达式

字符 含义 备注
abc 一个abc
[abcd] abcd中的一个即可
[a-z] a-z中的一个
123 一个123
[123] 123中的一个
[0-9] 0-9中的一个
[a-x0-9] a-z或0-9中的一个
[A-Za-Z0-9] 大写的A-Z或小写的a-z或者0-9中的一个
a[1-9] a1-a9
138[0-9] [0-9]

元字符

元字符
. 任意一个字符
\d 任意一个数字 相当于[0-9]
\s 一个空格
\b 单词边界
\w 一个字母数字或下划线甚至一个中文
\D 一个数字之外的字符
\S 不是一个空格
\W 不是一个字母数字或下划线甚至一个中文

量词

量词
a 表示aaa
abc 表示abccccc
d 表示dd或ddd或ddddd
+ 相当于{1,},一次以上
* 相当于{0,},任意次
？ 相当于{0,1}，有或者没有
特殊字符用\转义
\ . 一个点
\ + 一个加号
(abc|李四|小红){} abc 或 李四 或 小红
^abc 以a开头
abc$ 以c结尾
^abcd$ a开头d结尾的 abcd

案例：

qq邮箱：

[1-9]\d{4,9}@qq\ .com

表示一个13x 15x 18x开头的11位电话号码

1[358]\d{9}

表示一个小于1的正小数

0\ .\d+

表示一个带符号的实数

(\ +|\ -)?\d+(\ .\d+)?

Python正则

需要导入模块 import re

需要创键规则

需要用re的方法来寻找结果

re.search()

re.find()

在python中()代表捕获模式 ，(? : ) 这是不捕获

示例：

# datetime:2020/10/4 11:46
# 06正则表达式
import re
str2 = 'abcde'
print(str2.find('c'))
names = '张三-李四-王五-张三丰'.split('-')
print(names)
print([each for each in names if each[0]=='张'])
# 取出所有城市
string = '''
 <div class="e" name="area_channel_div_def" style="display:none">
        <span><a href="//www.51job.com/dalian/">大连</a></span>
        <span><a href="//www.51job.com/dongguan/">东莞</a></span>
        <span><a href="//www.51job.com/dandong/">丹东</a></span>
        <span><a href="//www.51job.com/daqing/">大庆</a></span>
        <span><a href="//www.51job.com/dazhou/">达州</a></span>
        <span><a href="//www.51job.com/datong/">大同</a></span>
        <span><a href="//www.51job.com/deyang/">德阳</a></span>
        <span><a href="//www.51job.com/dezhou/">德州</a></span>
        <span><a href="//www.51job.com/dongying/">东营</a></span>
        <span><a href="//www.51job.com/errduosi/">鄂尔多斯</a></span>
        <span><a href="//www.51job.com/ezhou/">鄂州</a></span>
        <span><a href="//www.51job.com/fuzhou/">福州</a></span>
        <span><a href="//www.51job.com/foshan/">佛山</a></span>
        <span><a href="//www.51job.com/fushun/">抚顺</a></span>
        <span><a href="//www.51job.com/fuzhoue/">抚州</a></span>
        <span><a href="//www.51job.com/fuyang/">阜阳</a></span>
    </div>
'''


str3 = 'a123b456b789b'
# 创建规则
reg = re.compile('[a-zA-Z]\d')
# 判断有没有
print(re.search(reg,str3))
# 把结果找出来,返回一个列表
result=re.findall(reg,str3)
print(result)
# 创键axxxb
str3 = 'a123b456b789b'
reg2=re.compile("a.+b")
print(re.findall(reg2,str3))
# 匹配模式：默认贪婪模式
# 非贪婪模式 .*?
reg3=re.compile('a.*?b')
print(re.findall(reg3,str3))#结果 ['a123b']

#以统一结构复制过来，想要保留什么，就把什么变成(.*?),去掉什么用 .*?
reg4=re.compile('/">(.*?)</a></span>')
result4=re.findall(reg4,string)
print(result4)

示例02：使用正则下载图片

# datetime:2020/10/4 15:52
# 07批量下载图片
import requests
import chardet
import random
import re
def getHtml(url):
    # 2.准备网址
    user_agent = [
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
        "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
        "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
        "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
        "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
        "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
        "UCWEB7.0.2.37/28/999",
        "NOKIA5700/ UCWEB7.0.2.37/28/999",
        "Openwave/ UCWEB7.0.2.37/28/999",
        "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
        # iPhone 6：
      "Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",

    ]
    # 3.访问网址
    res = requests.get(url,headers={'User-Agent':random.choice(user_agent)})
    # 获取编码
    encode = chardet.detect(res.content)
    # 4.设置编码
    res.encoding = encode.get('encoding')
    # 5.展示信息
    return res
# 准备地址
url = "http://www.netbian.com/fengjing/"
# 访问
res=getHtml(url)
# 创键正则
reg=re.compile('<img src="(.*?)" alt=".*?">')
#正则匹配得到结果
result = re.findall(reg,res.text)
from urllib import request
for index,each in enumerate(result):
    request.urlretrieve(each,f'F:\壁纸\{index}.jpg')

BeautifulSoup案例

# datetime:2020/10/4 16:35
# 08beautifulSoup
# 导入模块
from bs4 import BeautifulSoup

html = """  
<html>
<head> <title>The Dormouse's story</title> </head>  
<body>  
    <h1><b>123456</b></h1>
    <p class="title" name="dromouse">
        <b>The Dormouse's story</b>
        aaaaa
    </p> 
    <p class="title" name="dromouse" title='new'><b>The Dormouse's story</b>a</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>;
        <a href="http://example.com/tillie" class="siterr" id="link4">Tillie</a>;  
        <a href="http://example.com/tillie" class="siterr" id="link5">Tillie</a>;  
        and they lived at the bottom of a well.
    </p>  
    <p class="story">...</p>
    <ul id="ulone">
        <li>01</li>
        <li>02</li>
        <li>03</li>
        <li>04</li>
        <li>05</li>
    </ul>
    <div class='div11'>
        <ul id="ultwo">
            <li> 0001 </li>
            <li>0002</li>
            <li>0003</li>
            <li>0004</li>
            <li>0005</li>
        </ul>
    </div>
</body> 
</html>
"""
# 转为bs4对象
soup=BeautifulSoup(html,"html.parser")
print(soup)
# xxx找第一个yy标签
print(soup.title)
print(soup.find('title'))
# 标签的文本内容
print(soup.find('title').text)



# 根据id找对象
ul=soup.find(id='ulone')
print(ul)

# 根据class找对象,参数class 多个 下划线
print(soup.find(class_='title'))

# 细化寻找
print(soup.find('p',class_='title'))

# 通用写法
print(soup.find('p',attrs={'name':'dromouse'}))
print(soup.find('p',attrs={'name':'dromouse','title':'new'}))

# 获取多个 find_all
lis=soup.find_all('li')
print(lis)
#
# # 只找某个 内的li
print(soup.find(id='ulone').find_all('li'))
#
a=soup.find(class_='story').find('a')
print(a)
print(a.text)
print(a.attrs)
print(a.attrs['href'])

作业1

# datetime:2020/10/4 17:27
# 作业1
# 使用 requests+bs4 抓取 彼岸壁纸 图片链接，并存储到csv文件
import requests
import chardet
import random
from bs4 import BeautifulSoup
import csv
def getHtml(url):
    # 2.准备网址
    user_agent = [
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
        "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
        "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
        "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
        "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
        "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
        "UCWEB7.0.2.37/28/999",
        "NOKIA5700/ UCWEB7.0.2.37/28/999",
        "Openwave/ UCWEB7.0.2.37/28/999",
        "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
        # iPhone 6：
      "Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",

    ]
    # 3.访问网址
    res = requests.get(url,headers={'User-Agent':random.choice(user_agent)})
    # 获取编码
    encode = chardet.detect(res.content)
    # 4.设置编码
    res.encoding = encode.get('encoding')
    # 5.展示信息
    return res
# 准备地址
url = "http://www.netbian.com/fengjing/"
# 访问
res = getHtml(url)
html = res.text
soup = BeautifulSoup(html,"html.parser")
blist = []
over = soup.find(class_='list')
for link in over.find_all('img'):
    a = link.get('src')
    blist.append(a)
print(blist)

for i in blist:
    a=[[i]]
    with open('newcsv.csv', 'a', encoding='utf-8', newline='')as newfile:
        # 存储csv,读取的文件writer
        writer = csv.writer(newfile)
        writer.writerows(a)

作业2

# datetime:2020/10/4 17:27
# 作业1
# 使用 requests+bs4 抓取 彼岸壁纸 图片链接，并存储到csv文件
import requests
import chardet
import random
from bs4 import BeautifulSoup
import csv
def getHtml(url):
    # 2.准备网址
    user_agent = [
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
        "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
        "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
        "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
        "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
        "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
        "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
        "UCWEB7.0.2.37/28/999",
        "NOKIA5700/ UCWEB7.0.2.37/28/999",
        "Openwave/ UCWEB7.0.2.37/28/999",
        "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
        # iPhone 6：
      "Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",

    ]
    # 3.访问网址
    res = requests.get(url,headers={'User-Agent':random.choice(user_agent)})
    # 获取编码
    encode = chardet.detect(res.content)
    # 4.设置编码
    res.encoding = encode.get('encoding')
    # 5.展示信息
    return res
# 准备地址
def get(url):
    # 访问
    res = getHtml(url)
    html = res.text
    soup = BeautifulSoup(html,"html.parser")
    blist = []
    over = soup.find(class_='list')
    for link in over.find_all('img'):
        a = link.get('src')
        blist.append(a)
    print(blist)

    for i in blist:
        a=[[i]]
        with open('bian.csv', 'a', encoding='utf-8', newline='')as newfile:
            # 存储csv,读取的文件writer
            writer = csv.writer(newfile)
            writer.writerows(a)

if __name__ == "__main__":
    a = input('请输入要爬取的页数')
    get('http://www.netbian.com/fengjing/index_%s.htm' % (a))
posted @ 2020-10-05 17:37  秋弦  阅读(367)  评论(0)  编辑  收藏  举报