python爬虫requests上

3.用urlretrieve：

2.with open

import urllib.request
import urllib.parse
import requests
url ='https://image.baidu.com/search/detail?ct=503316480&z=0&ipn=d&word=python%20%E5%9C%A8%E5%BA%93%E9%87%8C%E9%9D%A2%E5%AE%89%E8%A3%85json&step_word=&hs=0&pn=0&spn=0&di=3200&pi=0&rn=1&tn=baiduimagedetail&is=0%2C0&istype=0&ie=utf-8&oe=utf-8&in=&cl=2&lm=-1&st=undefined&cs=3292127761%2C2561460082&os=1102035953%2C4035766811&simid=0%2C0&adpicid=0&lpn=0&ln=1195&fr=&fmq=1618834820344_R&fm=&ic=undefined&s=undefined&hd=undefined&latest=undefined&copyright=undefined&se=&sme=&tab=0&width=undefined&height=undefined&face=undefined&ist=&jit=&cg=&bdtype=15&oriquery=&objurl=https%3A%2F%2Fgimg2.baidu.com%2Fimage_search%2Fsrc%3Dhttp%3A%2F%2Fimg-blog.csdnimg.cn%2F20200526170234488.png%3Fx-oss-process%3Dimage%2Fwatermark%2Ctype_ZmFuZ3poZW5naGVpdGk%2Cshadow_10%2Ctext_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ZpY3RvcnkwOTQz%2Csize_16%2Ccolor_FFFFFF%2Ct_70%26refer%3Dhttp%3A%2F%2Fimg-blog.csdnimg.cn%26app%3D2002%26size%3Df9999%2C10000%26q%3Da80%26n%3D0%26g%3D0n%26fmt%3Djpeg%3Fsec%3D1621426988%26t%3D12927a841d449e0a8c00666fac19a8cb&fromurl=ippr_z2C%24qAzdH3FAzdH3Fooo_z%26e3Bvf1g_z%26e3BgjpAzdH3F2wpij6_dcAzdH3FMpTwM2afNDvyM3QpY4xeZoOaOaOOaOaO_z%26e3Bip4s&gsm=1&rpstart=0&rpnum=0&islist=&querylist=&force=undefined'
res =requests.get(url)
# fn =open('code.png','wb')
# fn.write(res.content)
# fn.close()
with open('code2.jpg','wb') as f:
    f.write(res.content)

方法三：urlretrieve

1.urllib——基础图片的爬取

urlib.request的使用

字节流数据转换——字节→str类型——bytes

import urllib.request
import urllib.parse
import requests
url = 'https://www.baidu.com/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'}
# 创建urllib.req请求对象
req = urllib.request.Request(url,headers=headers)
# 获取响应对象
res =urllib.request.urlopen(req)
html =res.read().decode('utf-8')
print(html)

urllib.parse的使用——转化中文处理

urllib.parse.urlencode（字典）

# url =https://www.baidu.com/s?wd=%E8%BF%AA%E5%8D%A2%E6%9C%A8%E5%A4%9A
# url =https://image.baidu.com/search/index?tn=baiduimage&ps=1&ct=201326592&lm=-1&cl=2&nc=1&word=迪卢姆多
wd ={'wd':'迪卢姆多'}
result =urllib.parse.urlencode(wd)
print(result)
base_url ='https://www.baidu.com/s?'
url =base_url +result
print(url)

urllib.parse.quote（str）

r ='迪卢姆多'
result =urllib.parse.quote(r)
print(r)
base_url ='https://www.baidu.com/s?'
url =base_url +result
print(url)

拓展：网页百分号：unquote：

需求：输入搜索内容，输出并保存html

urlencode——字典；quote——字符串

# 需求：搜索查询内容，输出+保存本地html
from urllib input request
import urllib.parse
base_url = 'https://www.baidu.com/s?'
key =input('请输入内容：’）
zidian ={'wb':key}
key1 =urllib.parse.urlencode(zidian)
url =base_url + key1
headers ={
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36
}
req =urllib.request.Request(url,headers =headers)
res =urllib.requset.urlopen(req)
html =res.read().decode('utf-8')
with open ('搜索页面信息.html'，'w',encoding ='utf-8') as f:
     f.write(html)

quote:

# 需求：把只能单一搜索内容换成其他内容
key =input('请输入搜索内容：')
wd ={'wd':key}
result =urllib.parse.urlencode(wd)
base_url ='https://www.baidu.com/s?'
url =base_url +result
print(url)

# 需求：把只能单一搜索内容换成其他内容
key =input('请输入搜索内容：')
wd ={'wd':key}
result =urllib.parse.urlencode(wd)
base_url ='https://www.baidu.com/s?'
url =base_url +result
# print(url)
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'}
req =urllib.request.Request(url,headers=headers)
res =urllib.request.urlopen(req)
html =res.read().decode('utf-8')
with open('搜索.html','w',encoding='utf-8') as f:
    f.write(html)

百度贴吧的练习html

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'}
name = input('请输入贴吧名:')
begin = int(input('请输入起始页'))
end = int(input('请输入结束页'))
kw = {'kw': name}
result = urllib.parse.urlencode(kw)
# 拼接url
for i in range(begin, end + 1):
    pn = (i - 1) * 50
    print(pn)
    base_url = 'https://tieba.baidu.com/f?'
    url = base_url + result + '&pn=' + str(pn)
    req =urllib.request.Request(url,headers=headers)
    res =urllib.request.urlopen(req)
    html = res.read().decode('utf-8')
    # html = res.read().decode('utf-8')
    filename = '第' +str(i) +'页.html'
    with open(filename,'w',encoding='utf-8') as  f:
        print('正在爬取%d页'% i)
        f.write(html)