Python爬虫—requests的使用及案例

pip install requests -i https://pypi.douban.com/simple

• 一个类型: Response
• 六个属性:
  • response.encoding = ‘utf-8’      设置网页编码格式
  • response.text          以字符串形式返回网页源码
  • response.url          获取请求的url
  • response.content           返回二进制数据
  • response.status_code      返回响应的状态码
  • response.headers           返回响应头

应用实例

import requests

url = 'https://www.baidu.com/s?'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'
}
data = {
    'wd':'北京'
}
response = requests.get(url=url,params=data,headers=headers)
content = response.text
print(content)

应用实例

import json
import requests

url = 'https://fanyi.baidu.com/sug'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'
}
data = {
    'kw':'eye'
}
response = requests.post(url=url,data=data,headers=headers)
content = response.text
obj = json.loads(content)
print(obj)

应用实例

import requests

url = 'https://www.baidu.com/s?'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'
}
data = {
    'wd':'ip'
}
proxy = {
    'http':'183.246.170.14:30001'
}
response = requests.get(url=url,params=data,headers=headers,proxies=proxy)
content = response.text
with open("daili.html","w",encoding="utf-8") as fp:
    fp.write(content)

import requests
from lxml import etree
from bs4 import BeautifulSoup

# 登录页面的地址
url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'
}
response  = requests.get(url=url,headers=headers)
content = response.text

tree = etree.HTML(content)

# (1) 获取 __VIEWSTATE
viewstate = tree.xpath('//input[@__VIEWSTATE"]/@value')
# (2) 获取 __VIEWSTATEGENERATOR
viewstategenerntor = tree.xpath('//input[@__VIEWSTATEGENERATOR"]/@value')

# (3) 获取验证码图片
code = tree.xpath('//img[@imgCode"]/@src')[0]
code_url = 'https://so.gushiwen.cn' + code
# 下载验证码图片到本地,然后输入
session = requests.session()
# 验证码的url内容
response_code = session.get(code_url)
# 注意此时要使用二进制，因为我们要使用图片的下载
content_code = response_code.content
with open("code.jpg", "wb") as fp:
    fp.write(content_code)

code_name = input('请输入你的验证码：')

# 点击登录
url_post = 'https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx'

data_post = {
    '__VIEWSTATE':viewstate,
    '__VIEWSTATEGENERATOR':viewstategenerntor,
    'from': 'http://so.gushiwen.cn/user/collect.aspx',
    'email': '15284124517',
    'pwd': 'xy251753',
    'code': code_name,
    'denglu': '登录'
}

response_post = session.post(url=url_post,headers=headers,data=data_post)
content_post = response_post.text

with open("gushiwen.html", "w", encoding='utf-8') as fp:
    fp.write(content_post)