import os
import requests
from bs4 import BeautifulSoup as bs
import time, random # 增加随机休息的时间来避免对于运营方的网络特别大的影响,也避免被封ip
class worm():
def __init__(self):
self.book_code = 782
self.book_code_list = [782, 801]
self.testFlag = True
self.testRange = range(0, 10)
self.basic_url = "https://www.xinshuhaige.org/" # 一定要有http
self.headers = [
'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:22.0) Gecko/20130328 Firefox/22.0",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1623.0 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36",
"Mozilla/5.0 (X11; NetBSD) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36",
"Mozilla/5.0 (Windows NT 5.0; rv:21.0) Gecko/20100101 Firefox/21.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1664.3 Safari/537.36",
"Opera/9.80 (Windows NT 5.1; U; cs) Presto/2.7.62 Version/11.01",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1944.0 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20130331 Firefox/21.0",
"Mo
python爬虫-源码
最新推荐文章于 2024-07-31 14:30:10 发布