requests-基础

get请求

import requests

response = requests.get('http://www.hnxmxit.com')

# 查看正文，二进制模式
# print(response.content.decode('utf-8'))

# print(response.text)  # 乱码  返回的是Unicode模式

response.encoding = 'utf-8'
print(response.text)


import requests

data = {"wd": "新梦想软测"}

headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
           'Accept-Encoding': 'gzip, deflate, br',
           'Accept-Language': 'zh-CN,zh;q=0.8',
           'Cookie': 'BIDUPSID=960CE33D3FF98A72CC0980AAB4111FC6; PSTM=1582429906; BAIDUID=3C9F7E8AAA25F1F408723A9B0FF10550:FG=1; COOKIE_SESSION=35712_11_6_5_10_9_0_1_5_5_0_0_605063_731225_0_6_1590289271_1590325433_1590325427%7C9%23731242_53_1590325427%7C9; BDRCVFR[cfqDsv-xoJY]=IdAnGome-nsnWnYPi4WUvY; delPer=0; BD_CK_SAM=1; PSINO=5; H_PS_PSSID=; BD_UPN=12314753; H_PS_645EC=5857EWgZqHqJcfItCTspyOUlCY242l79DbmbwILPm9skt6wFAcsYzfPAyXnBHIbmuk5nsBk; BDORZ=FFFB88E999055A3F8A630C64834BD6D0',
           'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.104 Safari/537.36}'
           }

response = requests.get('http://www.baidu.com/s', params=data, headers=headers)
response.encoding = 'utf-8'
print(response.text)```

字符串和字典的转换

import json
import jsonpath

#在python中字典可以认为是json对象

str_dict = {'name': 'xiaoming', 'age': 22}
str1 = json.dumps(str_dict)  # 将字典转换为字符串
print(type(str1))
print(str1)

str2 = json.loads(str1)  # 将字符串转换为字典
print(type(str2))
print(str2)```
## re模块

```python

import re

# 写法一
source_str = 'python1class'
# # match:如果正则表达式的0个或多个字符与正则表达式匹配的规则一致，则返回对应的match对象
# value = re.match('python\dc', source_str).group()
# # search:
# value_1 = re.search('thon\dc', source_str).group()
# print(value, value_1)

# 写法二
regexp = re.compile('thon\dc')
v = regexp.search(source_str).group()
print(v)

https://www.cnblogs.com/dream66/p/12953729.html


import re
str_1 = '<title>新梦想</title>'

regep = re.compile('t+')  # +重复一次或多次
result = regep.findall(str_1)
print(result)

regep_1 = re.compile('<title>(.+?)</title>')
result_1 = regep_1.findall(str_1)
print(result_1[0])

result_2 = re.findall('<title>(.+?)</title>', str_1)
print(result_2[0])