GET请求
1 import requests 2 3 headers = { 4 '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' 5 } 6 data = { 7 'wd': '码云' 8 } 9 url = "https://www.baidu.com/s"10 response = requests.get(url, headers=headers, params=data, verify=False)11 print(response.status_code)12 print(response.request.url)13 print(response.content.decode())
POST请求
1 import json 2 3 import requests 4 import urllib3 5 6 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) 7 headers = { 8 'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Mobile Safari/537.36' 9 10 }11 query_string = input("输入你要翻译的汉字:")12 data = {13 'query': query_string,14 'from': 'zh',15 'to': 'en'16 17 }18 url = 'https://fanyi.baidu.com/basetrans'19 response = requests.post(url=url, headers=headers, data=data, verify=False)20 # print(response.content.decode())21 22 dict_ret = json.loads(response.content.decode())23 ret = dict_ret['trans'][0]['dst']24 print(ret)
session登录
1 import requests 2 import urllib3 3 4 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) 5 session = requests.Session() 6 7 url = "https://login.m.taobao.com/login.htm" 8 headers = { 9 'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1'10 }11 data = {12 'TPL_username': "xxx",13 'TPL_password': "xxx"14 }15 session.post(url=url, headers=headers, data=data, verify=False)16 ret = session.get("https://h5.m.taobao.com/mlapp/olist.html", headers=headers, verify=False)17 with open('cart.html', 'w', encoding='utf-8') as f:18 f.write(ret.content.decode('utf-8'))
cookie登录
1 import requests 2 import urllib3 3 4 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) 5 6 headers = { 7 'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1', 8 'Cookie': 'isg=BHx8iHc6DAlbjzjWCQinbw9ITRru3SevFeYCa1b9iGdKIRyrfoXwL_KTBc9Zclj3' 9 }10 11 ret = requests.get("https://h5.m.taobao.com/mlapp/olist.html", headers=headers, verify=False)12 with open('cart.html', 'w', encoding='utf-8') as f:13 f.write(ret.content.decode('utf-8'))
cookie生成键值对
1 import requests 2 import urllib3 3 4 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) 5 url = 'https://h5.m.taobao.com/mlapp/olist.html' 6 headers = { 7 'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1', 8 } 9 10 cookies = 'thw=cn; t=d04efea3a8fd36e76208d492e2af8f43; '11 cookies = {i.split('=')[0]: i.split('=')[1] for i in cookies.split("; ")}12 13 print(cookies)14 ret = requests.get(url, headers=headers, cookies=cookies, verify=False)15 with open('cart.html', 'w', encoding='utf-8') as f:16 f.write(ret.content.decode('utf-8'))
cookiejar
1 import requests 2 import urllib3 3 4 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) 5 6 url = "https://www.baidu.com/" 7 headers = { 8 'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1' 9 }10 response = requests.get(url, headers=headers, verify=False)11 12 # 将CookieJar转为字典:13 cookies_dict = requests.utils.dict_from_cookiejar(response.cookies)14 print(cookies_dict)15 # 将字典转为CookieJar:16 # cookie_dict - 插入到CookieJar中的键/值的字典。17 # cookiejar - (可选)一个cookiejar来添加cookie。18 # 覆盖 - (可选)如果为False,则不会使用新的jar替换jar中已有的cookie。19 cookies = requests.utils.cookiejar_from_dict(cookies_dict, cookiejar=None, overwrite=True)20 print(cookies)21 22 # 转换完之后就可以把它赋给cookies 并传入到session中了:23 # s = requests.Session()24 # s.cookies = cookies25 #26 # print(s.cookies)
url地址解码
1 import requests 2 import urllib3 3 4 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) 5 6 url = 'https://www.baidu.com/s?word=人工智能' 7 8 ret = requests.utils.quote(url) 9 print(ret)10 11 ret = requests.utils.unquote(ret)12 print(ret)13 14 headers = {15 'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1'16 }17 response = requests.get(url, timeout=5, headers=headers, verify=False)18 print(response.content.decode())
异常重试
1 import requests 2 from retrying import retry 3 4 url = "http://www.youtube.com" 5 headers = { 6 'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1' 7 } 8 9 10 # 最大重试3次 异常捕获11 @retry(stop_max_attempt_number=3)12 def _parse_url(urls, method, data, proxies):13 if method == 'POST':14 response = requests.post(urls, headers=headers, data=data, timeout=3, proxies=proxies)15 else:16 response = requests.get(urls, headers=headers, data=data, timeout=3, proxies=proxies)17 assert response.status_code == 20018 return response.content.decode()19 20 21 def parse_url(urls, method='get', data=None, proxies={}):22 try:23 html_str = _parse_url(urls, method, data, proxies)24 except:25 html_str = None26 27 return html_str28 29 30 if __name__ == '__main__':31 print(parse_url(url))