Python爬蟲第四篇--Requests庫
阿新 • • 發佈:2018-11-30
Requests簡介
-
Requests是基於urllib的python庫,比urllib庫更方便
-
採用Apache2 Licensed開源協議的HTTP庫
-
MacOS安裝:pip3 install requests
例項
import requests
response = requests.get('https://www.baidu.com/')
print(type(response))
print(response.status_code)
print(type(response.text))
print(response.text)
print(response.cookies)
各種請求方法
import requests
requests.post('http://httpbin.org/post')
requests.put('http://httpbin.org/put')
requests.delete('http://httpbin.org/delete')
requests.head('http://httpbin.org/get')
requests.options('http://httpbin.org/get')
http測試網站:http://httpbin.org/,可以新增字尾
ip、uaer-agent、headers、get、post、patch、put、delete
等獲取相應測試資訊
請求
基本GET請求
- GET基本寫法
import requests
response = requests.get('http://httpbin.org/get')
print(response.text)
- 帶參GET
import requests
response = requests.get('http://httpbin.org/get?name=germey&age=22')
print(response.text)
import requests
data = {
'name':'germay' ,
'age':22
}
response = requests.get('http://httpbin.org/get',params=data)
print(response.text)
- 解析Json
import requests
import json
response = requests.get('http://httpbin.org/get')
print(type(response.text))
print(response.json())
print(json.loads(response.text))
print(type(response.json()))
- 獲取二進位制資料
import requests
response = requests.get('https://github.com/favicon.ico')
print(type(response.text),type(response.content))
print(response.text)
print(response.content)
import requests
response = requests.get('https://github.com/favicon.ico')
with open('favicon.ico','wb') as f:
f.write(response.content)
f.close()
- 新增headers
import requests
response = requests.get('https://www.zhihu.com/explore')
print(response.text)
import requests
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.get("https://www.zhihu.com/explore", headers=headers)
print(response.text)
基本POST請求
import requests
data = {'name': 'germey', 'age': '22'}
response = requests.post("http://httpbin.org/post", data=data)
print(response.text)
import requests
data = {'name': 'germey', 'age': '22'}
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.post("http://httpbin.org/post", data=data, headers=headers)
print(response.json())
響應
response屬性
import requests
response = requests.get('http://www.jianshu.com')
print(type(response.status_code), response.status_code)
print(type(response.headers), response.headers)
print(type(response.cookies), response.cookies)
print(type(response.url), response.url)
print(type(response.history), response.history)
狀態碼判斷
import requests
response = requests.get('http://www.jianshu.com/hello.html')
exit() if not response.status_code == requests.codes.not_found else print('404 Not Found')
import requests
response = requests.get('http://www.jianshu.com')
exit() if not response.status_code == 200 else print('Request Successfully')
高階操作
檔案上傳
import requests
files = {'file':open('favicon.ico','rb')}
response = requests.post('http://httpbin.org/post',files=files)
print(response.text)
獲取cookie
import requests
response = requests.get("https://www.baidu.com")
print(response.cookies)
for key, value in response.cookies.items():
print(key + '=' + value)
會話維持
- 模擬登陸
import requests
requests.get('http://httpbin.org/cookies/set/number/123456789')
response = requests.get('http://httpbin.org/cookies')
print(response.text)
import requests
s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)
證書驗證
import requests
response = requests.get('https://www.12306.cn')
print(response.status_code)
import requests
from requests.packages import urllib3
urllib3.disable_warnings()
response = requests.get('https://www.12306.cn', verify=False)
print(response.status_code)
import requests
response = requests.get('https://www.12306.cn', cert=('/path/server.crt', '/path/key'))
print(response.status_code)
代理設定
MacOS安裝:pip3 install 'requests[socks]'
import requests
proxies = {
"http": "http://127.0.0.1:9743",
"https": "https://127.0.0.1:9743",
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)
import requests
proxies = {
"http": "http://user:[email protected]:9743/",
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)
import requests
proxies = {
'http': 'socks5://127.0.0.1:9742',
'https': 'socks5://127.0.0.1:9742'
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)
超時設定
import requests
from requests.exceptions import ReadTimeout
try:
response = requests.get("http://httpbin.org/get", timeout = 0.5)
print(response.status_code)
except ReadTimeout:
print('Timeout')
認證設定
import requests
from requests.auth import HTTPBasicAuth
r = requests.get('http://120.27.34.24:9001', auth=HTTPBasicAuth('user', '123'))
print(r.status_code)
import requests
r = requests.get('http://120.27.34.24:9001', auth=('user', '123'))
print(r.status_code)
異常處理
import requests
from requests.exceptions import ReadTimeout, ConnectionError, RequestException
try:
response = requests.get("http://httpbin.org/get", timeout = 0.5)
print(response.status_code)
except ReadTimeout:
print('Timeout')
except ConnectionError:
print('Connection error')
except RequestException:
print('Error')