def get_info(ip, port): # 获取代理IP的详细信息
url = CHECHINFO_IP
headers = get_headers()
proxies = {
'http': 'http://{ip}:{port}'.format(ip=ip, port=port),
'https': 'http://{ip}:{port}'.format(ip=ip, port=port)
}
params = {'ip': ip}
try:
start_time = time.time()
resp = requests.get(url,
headers=headers,
params=params,
proxies=proxies,
timeout=15).json()
end_time = time.time()
speed = '%.2f' % (end_time - start_time)
text = resp['data']
if text['country'] and text['region']:
country = text['country']
region = text['region']
city = text['city']
isp = text['isp']
return country, region, city, isp, speed
else:
return None
except BaseException as e:
print(e)
return None
def crawl_github(url):
headers = get_headers()
try:
resp = requests.get(url, headers=headers, timeout=15).text
contents = resp.split('\n')[:-2]
ip = []
port = []
types = []
protocol = []
for i in contents:
test = json.loads(i)
if test['country'] == 'CN':
ip.append(test['host'])
port.append(test['port'])
if test['anonymity'] == 'high_anonymous':
types.append('高匿')
elif test['anonymity'] == 'anonymous':
types.append('匿名')
else:
types.append('透明')
protocol.append(test['type'].upper())
return zip(ip, port, types, protocol)
except BaseException as e:
# print(e)
return None
def download(self, url):
print("Download:{}".format(url)) # 因为url在变化，所以要用异常处理
r = requests.get(url, headers=get_headers(), timeout=10)
# print(chardet.detect(r.content)) # 识别编码过程{'encoding': 'utf-8', 'confidence': 0.99, 'language': ''}
r.encoding = chardet.detect(r.content)["encoding"] # 解对应编码
if r.status_code == 200 or len(r.content) > 500: # 如果访问成功
return r.text # 返回文本
def crawl_cloud(url): # 爬取云代理免费代理
headers = get_headers()
try:
resp = session.get(url, headers=headers)
contents = resp.html.find('#list tr')[1:]
ip = []
port = []
proxy_kind = []
proxy_type = []
for i in range(len(contents)):
items = contents[i]
contents_list = items.text.split('\n')
ip.append(contents_list[0])
port.append(contents_list[1])
proxy_kind.append('高匿')
proxy_type.append(contents_list[3])
return list(zip(ip, port, proxy_kind, proxy_type))
except BaseException as e:
# print(e)
return None
def check_ip(ip, port): # 检测代理IP是否可用
url = TEST_IP
headers = get_headers()
proxies = {
'http': 'http://{ip}:{port}'.format(ip=ip, port=port),
'https': 'http://{ip}:{port}'.format(ip=ip, port=port)
}
try:
start_time = time.time()
resp = requests.get(url, headers=headers, proxies=proxies,
timeout=15).text
end_time = time.time()
speed = '%.2f' % (end_time - start_time)
if ip == json.loads(resp.replace(';',
'').split('=')[-1].strip())['cip']:
return speed
else:
return None
except:
return None
def check_proxy(redis_to, ip_port, zname, url=None):
if not url:
url = "https://www.baidu.com"
ip, port, *_ = ip_port.split(":")
proxies = {"http": f"http://{ip}:{port}", "https": f"http://{ip}:{port}"}
print("开始检测", ip_port)
start_time = time.time()
try:
res = requests.get(url=url,
headers=config.get_headers(),
proxies=proxies,
verify=False)
if res.status_code == 200:
# speed = round(time.time() - start_time, 3)
speed = int(time.time() - start_time)
print(f"响应时间为 {speed}，可用代理{proxies}")
change_score(redis_to, ip_port, zname, str(speed), 1)
except Exception:
change_score(redis_to, ip_port, zname, "1001", 0)
import json
import requests
from config import get_headers
from requests_html import HTMLSession
from util.browsertool import create_browser, select_em
header = get_headers()
urls = 'http://www.xicidaili.com/nn/1'
session = HTMLSession()
def crawl_xici(url): # 爬取西刺免费代理
headers = get_headers()
try:
resp = session.get(url, headers=headers)
contents = resp.html.find('#ip_list tr')[1:]
ip = []
port = []
proxy_kind = []
proxy_type = []
for i in range(len(contents)):
items = contents[i]
contents_list = items.text.split('\n')
ip.append(contents_list[0])
port.append(contents_list[1])
if len(contents_list) >= 7:
proxy_kind.append(contents_list[3])
proxy_type.append(contents_list[4])
else:
# -*- coding:utf-8 -*-
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from config import get_headers
from selenium import webdriver
headers = get_headers()
# 创建一个浏览器引擎
def create_browser(op_type):
if op_type == 'close':
chrome_options = webdriver.ChromeOptions()
# mobile_emulation = {"deviceName": "Galaxy S5"}
chrome_options.add_argument('--headless')
# chrome_options.add_experimental_option("mobileEmulation", mobile_emulation)
chrome_options.add_argument('--disable-gpu')
chrome_options.add_argument('disable-infobars')
chrome_options.add_argument('--disable-dev-shm-usage')
chrome_options.add_argument('--no-sandbox')
for key, value in headers.items():
chrome_options.add_argument(key + '=' + value)
browser = webdriver.Chrome(chrome_options=chrome_options)
browser.delete_all_cookies()
return browser
elif op_type == 'open':
chrome_options = webdriver.ChromeOptions()
# mobile_emulation = {"deviceName": "Galaxy S5"}
def download(url):
print("Download:{}".format(url)) # 因为url在变化，所以要用异常处理
r = requests.get(url, headers=get_headers(), timeout=10)
r.encoding = chardet.detect(r.content)["encoding"] # 解对应编码
if r.status_code == 200 or len(r.content) > 500: # 如果访问成功
return r.text # 返回文本
