利用Python解决GitHub访问速度慢的问题
GitHub访问速度慢，下载慢，可以在https://www.ipaddress.com/查询最新的GitHub地址，通过向Host文件添加记录的方式解决。
需要同时向Host文件添加"github.com", "github-cloud.s3.amazonaws.com", "codeload.github.com", "github.global.ssl.fastly.net","github-cloud.s3.amazonaws.com"五条记录
另外为了更方便获取地址，我写了一段Python代码，来爬取地址。
1 import os 2 from urllib import request 3 from lxml import etree 4 import ssl 5 from urllib.error import HTTPError 6 import time 7 8 9 def Path(pages: str) -> list: 10 return etree.HTML(pages).xpath('.//ul[@class="comma-separated"]/li/text()') 11 12 13 def CreatUrlList(urls: list) -> list: 14 lists = [] 15 for line in urls: 16 lists.append(f"https://{line}.ipaddress.com") 17 return lists 18 19 20 def GetIp(page_url: str) -> str: 21 try: 22 23 context1 = ssl._create_unverified_context() 24 r = request.urlopen(page_url, context=context1) 25 page = r.read().decode() 26 html = Path(page) 27 return list(set(html))[0] 28 except HTTPError as er: 29 print(er.code) 30 31 32 url_list = ["github.com", "github-cloud.s3.amazonaws.com", "codeload.github.com", "github.global.ssl.fastly.net", 33 "github-cloud.s3.amazonaws.com"] 34 35 36 if __name__ == '__main__': 37 lists_url = CreatUrlList(url_list) 38 lists = [] 39 # 在py文件目录下生产一个host.txt文件以便大家添加Host记录 40 path = os.getcwd() + "/host.txt" 41 print(path) 42 file = open(path, 'w', encoding="utf-8") 43 now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) 44 file.write(f"# GitHub网址爬取 {now}\n", ) 45 for url in lists_url: 46 ip = GetIp(url) 47 url = ip + "\t" + url.replace("https://", "").replace(".ipaddress.com", "") 48 try: 49 file.write(url + "\n") 50 except Exception as e: 51 print(e) 52 finally: 53 print(url) 54 file.close() 55 print("GitHub地址爬取完成！")
运行结果如下：
C:\Python\Python38\python.exe "C:/Users/Albert Yu/PycharmProjects/untitled/ipaddress.py" C:\Users\Albert Yu\PycharmProjects\untitled\host.txt 140.82.112.3 github.com 52.217.37.164 github-cloud.s3.amazonaws.com 140.82.113.10 codeload.github.com 199.232.69.194 github.global.ssl.fastly.net 52.217.37.164 github-cloud.s3.amazonaws.com GitHub地址爬取完成！ Process finished with exit code 0
