全网最全！Python爬虫requests库教程(附案例)_python requests(2)

requests.delete(“http://httpbin.org/delete”) #DELETE请求
requests.head(“http://httpbin.org/get”) #HEAD请求
requests.options(“http://httpbin.org/get”) #OPTIONS请求

import requests
r = requests.get(http://httpbin.org/get)
print(r.text)
{
“args”: {},
“headers”: {
“Accept”: “*/*”,
“Accept-Encoding”: “gzip, deflate”,
“Host”: “httpbin.org”,
“User-Agent”: “python-requests/2.24.0”,
“X-Amzn-Trace-Id”: “Root=1-5fb5b166-571d31047bda880d1ec6c311”
},
“origin”: “36.44.144.134”,
“url”: “http://httpbin.org/get”
}

import requests
response = requests.get(’https://www.zhihu.com/explore’)
print(f"当前请求的响应状态码为：{response.status_code}")
print(response.text)

import requests
headers = {“user-agent”: ’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36’}
response = requests.get(’https://www.zhihu.com/explore’, headers=headers)
print(f"当前请求的响应状态码为：{response.status_code}")

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/54.0.2840.99 Safari/537.36”}

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

print(response.request.headers)

import requests
headers = {“User-Agent”: “Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36”}
url = ’https://www.baidu.com/s?wd=python’
response = requests.get(url, headers=headers)

import requests
headers = {“User-Agent”: “Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36”}

url = ’https://www.baidu.com/s?’

kw = {’wd’: ’python’}

response = requests.get(url, headers=headers, params=kw)
print(response.content)

import requests
r = requests.get(“http://httpbin.org/get”)
print( type(r.text))
print(r.json())
print( type(r. json()))

import requests
headers = {’User-Agent’: ’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36’}
wd = ’张三同学’
pn = 1
response = requests.get(’https://www.baidu.com/s’, params={’wd’: wd, ’pn’: pn},
headers=headers)
print(response.url)

C%E5%AD%A6&pn=1

import requests
from urllib.parse import urlencode
headers = {’User-Agent’: ’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko)
wd = ’张三同学’
encode_res = urlencode({’k’: wd}, encoding=’utf-8’)
keyword = encode_res.split(’=’)[1]
print(keyword)

url = ’https://www.baidu.com/s?wd=%s&pn=1’ % keyword
response = requests.get(url, headers=headers)
print(response.url)

%90%8C%E5%AD%A6&pn=1

import requests
import re
headers = {“user-agent”: ’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36’}
response = requests.get(’https://www.zhihu.com/explore’, headers=headers)
result = re.findall(“(ExploreSpecialCard-contentTitle|ExploreRoundtableCard
questionTitle).*?>(.*?)”, response.text)
print([i[1] for i in result])

import requests
response = requests.get(“https://github.com/favicon.ico”)
with
open(’github.ico’, ’wb’) as f:
f.write(response.content)

import requests
url = ’https://www.baidu.com’
req = requests.get(url)
print(req.cookies)

for key, value in req.cookies.items():
print(f"{key} = {value}")

import requests
import re

headers = {

“user-agent”: ’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (
KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36’,

“cookie”: ’xxx这里是复制过来的cookie字符串’}

response = requests.get(’https://www.zhihu.com/creator’, headers=headers)
data = re.findall(’CreatorHomeAnalyticsDataItem-title.*?>(.*?)’,response.text)
print(response.status_code)
print(data)

import requests
import re
headers = {“user-agent”: ’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36’}
response = requests.get(’https://www.zhihu.com/creator’, headers=headers)
data = re.findall(’CreatorHomeAnalyticsDataItem-title.*?>(.*?)’,response.text)
print(response.status_code)
print(data)

response = requests.get(url, cookies)
import requests
import re
url = ’https://www.zhihu.com/creator’
cookies_str = ’复制的cookies’
headers = {“user-agent”: ’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36’}
cookies_dict = {cookie.split(’=’, 1)[0]:cookie.split(’=’, 1)[-1] for cookie in
cookies_str.split(’; ’)}

resp = requests.get(url, headers=headers, cookies=cookies_dict)
data = re.findall(’CreatorHomeAnalyticsDataItem-title.*?>(.*?)’,resp.text)
print(resp.status_code)
print(data)

import requests
import re
url = ’https://www.zhihu.com/creator’
cookies_str = ’复制的cookies’
headers = {“user-agent”: ’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36’}
jar = requests.cookies.RequestscookieJar()
for cookie in cookies_str.split(’;’):
key,value = cookie.split(’=’,1)
jar. set(key,value)

resp = requests.get(url, headers=headers, cookies=jar)
data = re.findall(’CreatorHomeAnalyticsDataItem-title.*?>(.*?)’,resp.text)
print(resp.status_code)
print(data)

import requests
import re
url = ‘https://www.zhihu.com/creator’
cookies_str = ‘复制的cookies’
headers = {“user-agent”: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36’}
cookie_dict = {cookie.split(‘=’, 1)[0]:cookie.split(‘=’, 1)[-1] for cookie in
cookies_str.split('; ')}

resp = requests.get(url, headers=headers, cookies=cookies_dict)
data = re.findall(‘CreatorHomeAnalyticsDataItem-title.*?>(.*?)’,resp.text)
print(resp.status_code)
print(data)

cookiejar = requests.utils.cookiejar_from_dict(cookie_dict, cookiejar=None,
overwrite=True)
type(cookiejar) # requests.cookies.RequestscookieJar
type(resp.cookies) # requests.cookies.RequestscookieJar
#构造RequestscookieJar对象进行cookies设置其中jar的类型也是 requests.cookies.
RequestscookieJar
#cookiejar转字典
requests.utils.dict_from_cookiejar(cookiejar)

import requests
payload = {’key1’: ’value1’, ’key2’: ’value2’}
req = requests.post(“http://httpbin.org/post”, data=payload)
print(req.text)

import json
import requests
url = ’http://httpbin.org/post’
payload = {’some’: ’data’}
req1 = requests.post(url, data=json.dumps(payload))
req2 = requests.post(url, json=payload)
print(req1.text)
print(req2.text)

url = ‘http://httpbin.org/post’
files = {‘file’: open(‘test.xlsx’, ‘rb’)}
req = requests.post(url, files=files)
req.text

import requests

kw =
input(“请输入要翻译的词语：”)
ps = {“kw”: kw}

headers = {

爬虫请求

“User-Agent”: “Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (
KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36 Edg/85.0.564.41”
}

response = requests.post(“https://fanyi.baidu.com/sug”, data=ps)

print(response.content.decode(“unicode_escape”))

import requests
import re

headers = {
‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (
KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36’,}

session = requests.session()

response = session.get(https://github.com/login, headers=headers)
authenticity_token = re.search(‘name=“authenticity_token” value=“(.*?)” />’,
response.text).group(1) # 使用正则获取登陆请求所需参数

data = {
‘commit’: ‘Sign in’, # 固定值
‘utf8’: ’ ', # 固定值
‘authenticity_token’: authenticity_token, # 该参数在登陆页的响应内容中
‘login’:
input(‘输入github账号：’),
‘password’:
input(‘输入github账号：’)}

session.post(https://github.com/session, headers=headers, data=data)

response = session.get(https://github.com/settings/profile, headers=headers)
print(response.text)