91av视频/亚洲h视频/操亚洲美女/外国一级黄色毛片 - 国产三级三级三级三级

  • 大小: 18KB
    文件類型: .py
    金幣: 2
    下載: 1 次
    發布日期: 2021-06-18
  • 語言: Python
  • 標簽:

資源簡介

僅僅只是教學源碼,并非專業爬蟲 所用到庫,requests,bs4,re,json,time,os 代碼可運行,可適當根據自身情況調整爬取頻率,即 time.sleep() 中的間隔時間

資源截圖

代碼片段和文件信息

from?bs4?import?BeautifulSoup
import?requests
import?os
import?re
import?json
import?time

start_date?=?‘20190316‘
end_date?=?‘20190330‘
days_list1?=?[312831303130313130313031]??#?平年每月的天數列表
days_list2?=?[312931303130313130313031]
turn?=?0
total_length?=?187935

def?UAPool():
????global?turn??#?用于切換用戶代理
????agents?=?[‘Mozilla/5.0?(Windows?NT?10.0;?Win64;?x64)?AppleWebKit/537.36?(KHTML?like?Gecko)?Chrome/80.0.3987.116?Safari/537.36‘
??????????????‘Mozilla/5.0?(Windows?NT?10.0;?WOW64)?AppleWebKit/537.36?(KHTML?like?Gecko)?Chrome/75.0.3770.100?Safari/537.36‘
??????????????‘Mozilla/5.0?(Windows?NT?10.0;?WOW64)?AppleWebKit/537.36?(KHTML?like?Gecko)?Chrome/78.0.3904.108?Safari/537.36?QIHU?360SE‘
??????????????‘Mozilla/5.0?(Windows?NT?10.0;?Win64;?x64)?AppleWebKit/537.36?(KHTML?like?Gecko)?Chrome/70.0.3538.102?Safari/537.36?Edge/18.18363‘
??????????????‘Mozilla/5.0?(Windows?NT?10.0;?Win64;?x64;?ServiceUI?14)?AppleWebKit/537.36?(KHTML?like?Gecko)?Chrome/70.0.3538.102?Safari/537.36?Edge/18.18363‘
??????????????‘Mozilla/5.0?(Windows?NT?10.0;?Win64;?x64)?AppleWebKit/537.36?(KHTML?like?Gecko)?Chrome/78.0.3904.70?Safari/537.36‘
??????????????‘Mozilla/5.0?(Macintosh;?U;?Intel?Mac?OS?X?10_6_8;?en-us)?AppleWebKit/534.50?(KHTML?like?Gecko)?Version/5.1?Safari/534.50‘
??????????????‘Mozilla/5.0?(Macintosh;?Intel?Mac?OS?X?10.6;?rv:2.0.1)?Gecko/20100101?Firefox/4.0.1?Firefox?4.0.1?–?Windows‘
??????????????‘Mozilla/5.0?(Windows;?U;?Windows?NT?6.1;?en-us)?AppleWebKit/534.50?(KHTML?like?Gecko)?Version/5.1?Safari/534.50‘
??????????????‘Opera/9.80?(Windows?NT?6.1;?U;?en)?Presto/2.8.131?Version/11.11?Chrome?17.0?–?MAC‘
??????????????‘Mozilla/5.0?(Macintosh;?Intel?Mac?OS?X?10_7_0)?AppleWebKit/535.11?(KHTML?like?Gecko)?Chrome/17.0.963.56?Safari/535.11‘
??????????????]
????turn?+=?1
????return?{‘User-Agent‘:agents[turn?%?11]}


def?CreateDate(start_date?end_date):??#?制作日期列表避免出現跨月份或者跨年份的日期使得url錯誤

????print(‘CreateDate開始‘)
????date_list?=?[]??#?存放最終日期列表
????days_list?=?[]

????year1?=?int(start_date[:4])
????month1?=?int(start_date[4:6])
????day1?=?int(start_date[6:])

????year2?=?int(end_date[:4])
????month2?=?int(end_date[4:6])
????day2?=?int(end_date[6:])

????for?i?in?range(year1?year2?+?1):
????????if?(i?%?4?==?0?and?i?%?100?!=?0)?or?i?%?400?==?0:??#?閏年
????????????if?year2?>?year1?and?i?==?year1:
????????????????days_list.append(days_list2[month1?-?1:])

????????????elif?year2?==?year1:
????????????????days_list.append(days_list2[month1?-?1:month2])

????????????elif?year2?>?year1?and?i?==?year2:
????????????????days_list.append(days_list2[:month2])

????????????else:
????????????????days_list.append(days_list2[::])

????????else:
????????????if?year2?>?year1?and?i?==?year1:
????????????????days_list.append(days_list1[month1?-?1:])

????????????elif?year2?==?year1:
????????????????days_list.append(days_list1[month1?-?1:month2])

????????????elif?year2?>?year1?and

評論

共有 條評論