jb51(脚本之家) pdf 网页存活情况检查 (非百度云链接检查)

jb51_books_check.py

import requests
import urllib
import re
import sys

def getInfo(book_id):
    url = "https://www.jb51.net/books/"+str(book_id)+".html"
    res = requests.get(url)

    res.encoding = "GBK"
    pattern = re.compile("<h1 itemprop=\"name\">(.*?)</h1>")
    book_name = re.findall(pattern, res.text)

    if len(book_name) != 0:
        return { "id": book_id, "name": book_name[0] }
    return { "id": book_id, "name": "" }

def scan(beg, end):
    total = end - beg
    res = []
    for idx in range(int(beg), int(end)):
        info = getInfo(idx)
        if info["name"] != "":
            res.append(info)
            print("[success]("+str(idx-beg)+"/"+str(total)+"): "+info["name"])
        else:
            print("[failed_]("+str(idx-beg)+"/"+str(total)+"): "+"[x]")
    return res

def logoutput(res):
    res = [str(elem["id"])+" -> "+elem["name"] for elem in res]
    with open("book.log", "w", encoding="utf-8") as f:
        for elem in res:
            f.write(elem + "\n")

if __name__ == "__main__":
    beg = int(sys.argv[1])
    end = int(sys.argv[2])

    print("Begin to scan:")
    res = scan(beg, end)
    logoutput(res)