002 requests的使用方法以及xpath和beautifulsoup4提取数据

1、直接使用url，没用headers的请求

import requests

url = 'http://www.baidu.com'
# requests请求用get方法
response = requests.get(url)

# 返回的content是字节 需要解码
data = response.content.decode()
print(data)
# 而text返回的是字符串类型
data = response.text
print(data)

只有url的代码

2、有headers的GET请求

requests的get参数，headers传入的参数是字典，不用转成字符串

import requests

url = 'http://www.baidu.com'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',

}
# requests请求用get方法
response = requests.get(url, headers=headers)

# 1. 获取请求头
print(response.request.headers)
# 2. 获取相应头
print(response.headers)
# 3. 获取状态码
print(response.status_code)
# 4. 请求的cookie
print(response.request._cookies)
# 5. 相应的cookie
print(response.cookies)

含有headers的代码

而 url = 'http://www.baidu.com/s?wd=你好' 中的汉字会自动转义，不需要调用其他模块

import requests

url = 'http://www.baidu.com/s?wd=你好'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
}
# requests请求用get方法
response = requests.get(url, headers=headers)

data = response.content.decode()
print(data)

在url后面直接拼接

import requests

url = 'http://www.baidu.com/'
params = {
    'wd': '你好',
}
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
}
# requests请求用get方法
response = requests.get(url, headers=headers, params=params)

data = response.content.decode()
print(data)

运用params字典类型进行拼接url

import requests

url = 'http://baidu.com'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
}
params = {
    'wd': '你好'
}
free_proxy = {
    'https': '153.232.156.201:8080',
}
# 加代理IP
response = requests.get(url, headers=headers, params=params, proxies=free_proxy)

data = response.content
print(data.decode())

代理IP

3、有headers的POST请求

import requests

url = 'http://iclass.ncut.edu.cn/iclass/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
}
data = {
    'login': '',
    'password': '******',
}
# requests请求用post方法
response = requests.post(url, headers=headers, data=data)

data = response.content
with open('01 登录界面.html', 'wb') as fp:
    fp.write(data)

登录含有cookie的代码

4、使用xpath提取数据

import requests
from lxml import etree

url = 'https://www.qiushibaike.com/text/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
}

response = requests.get(url, headers=headers)
data = response.content

# 1. 转解析类型
xpath_data = etree.HTML(data)

# 2. 调用xpath的方法
div_list = xpath_data.xpath('//div[@class="col1"]/div')
for div in div_list:
    author = div.xpath('.//div[@class="author clearfix"]/a[2]/h2/text()')[0].strip('\n')
    # 打印作者名
    print(author)

提取作者名的代码

5、使用beautifulsoup提取信息

from bs4 import BeautifulSoup

html_doc = '''
<div id="menu" class="menu-bar menu clearfix" style="margin:0 10px">
<a  href="/" target="_blank" rel="nofollow">热门</a>
<a  href="/hot/" target="_blank">24小时</a>
<a  href="/imgrank/" target="_blank">热图</a>
<a  id="highlight"  href="/text/" target="_blank">文字</a>
<a  href="/history/" target="_blank">穿越</a>
<a  href="/pic/" target="_blank">糗图</a>
<a  href="/textnew/" target="_blank">新鲜</a>
</div>
'''
# 1、转类型
soup = BeautifulSoup(html_doc, 'lxml')

# 2、格式化输出
result = soup.prettify()
# print(result)

# 3、取标签
print(soup.a)

# 4、取文本
print(soup.a.string)

# 5、取属性
print(soup.a['target'])

bu4代码

from bs4 import BeautifulSoup

html_doc = '''
<div id="menu" class="menu-bar menu clearfix" style="margin:0 10px">
<a  href="/" target="_blank" rel="nofollow">热门</a>
<a  href="/hot/" target="_blank">24小时</a>
<a  href="/imgrank/" target="_blank">热图</a>
<a  id="highlight"  href="/text/" target="_blank">文字</a>
<a  href="/history/" target="_blank">穿越</a>
<a  href="/pic/" target="_blank">糗图</a>
<a  href="/textnew/" target="_blank">新鲜</a>
</div>
'''
# 1、转类型
soup = BeautifulSoup(html_doc, 'lxml')

# 2、通用解析方法

# find  返回符合查询条件的第一个标签
print(soup.find(name='a'))
print(soup.find(attrs={"target": '_blank'}))

# find_all  返回list(标签对象)
print(soup.find_all(name='a', limit=3))

# select_one 返回css的选中器
print(soup.select_one('.menu'))

# select 返回的是list
print(soup.select('#highlight'))
print(soup.select('a[target="_blank"]'))

查找标签

6、其他常用知识点

查看response的编码格式

print(page_text.encoding)