#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
@File:csdn_reads.py
@E-mail:364942727@qq.com
@Time:2020/4/16 10:03 下午
@Author:Nobita
@Version:1.0
@Desciption:None
"""
import re
import time
import random
import requests
import urllib.request
from bs4 import BeautifulSoup
user_agent_list = [
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/61.0",
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15",
]
firefoxHead = {"User-Agent": user_agent_list}
firefoxHead['User-Agent'] = random.choice(user_agent_list)
IPRegular = r"(([1-9]?\d|1\d{2}|2[0-4]\d|25[0-5]).){3}([1-9]?\d|1\d{2}|2[0-4]\d|25[0-5])"
host = "https://blog.csdn.net"
url = "https://blog.csdn.net/hz90s/article/details/{}"
code = ["105518260"]
def parseIPList(url="http://www.xicidaili.com/"):
IPs = []
request = urllib.request.Request(url, headers=firefoxHead)
response = urllib.request.urlopen(request)
soup = BeautifulSoup(response, "html.parser")
tds = soup.find_all("td")
for td in tds:
string = str(td.string)
if re.search(IPRegular, string):
IPs.append(string)
return IPs
def PV(code):
s = requests.Session()
s.headers = firefoxHead['User-Agent']
count = 0
while True:
count += 1
print("asking for {} times\t".format(count), end="\t")
IPs = parseIPList()
s.proxies = {"http": "{}:8080".format(IPs[random.randint(0, 40)])}
s.get(host)
r = s.get(url.format(code))
html = r.text
soup = BeautifulSoup(html, "html.parser")
spans = soup.find_all("span")
print(spans[2].string)
time.sleep(random.randint(60, 75))
def main():
PV(code[0])
if __name__ == "__main__":
main()
