li604261234 发表于 2021-3-12 09:27

GANXIE

deng5762587 发表于 2021-3-14 23:48

感谢大神分享啊

17717293676 发表于 2021-3-15 01:15

小手一抖，金币拿走

QIUZHIQIANG 发表于 2021-3-15 01:28

646927165

2777958151@qq.c 发表于 2021-3-18 14:25

666666

cycnhwan 发表于 2021-3-18 15:16

{:1_329:}

li990219 发表于 2021-3-21 20:56

6666666666666

531430062 发表于 2021-3-25 20:08

很多老歌

13307826635 发表于 2021-3-29 06:35

6666666

ZHANGHE 发表于 2021-3-29 13:10

import requests
from bs4 import BeautifulSoup


def getUrl():
    headers = {
      "referer": "https://www.baidu.com/link?url=GgeDs1AzZQg7jAVgRWaaQVemNzUYNHFpN-PiFmUIyUHeaMQeoPb14_8g1oL7GmBggm70mm4e2EkM5F7lmQMUVq&wd=&eqid=fdcd73c000068a5900000004605ac987",
      "upgrade-insecure-requests": "1",
      "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0"
    }
    url = 'https://www.tupianzj.com/meinv/mm/nkmv/'

    urllist = []
    H = requests.get(url, headers=headers).text

    soup = BeautifulSoup(H, 'lxml').select('ul.d1.ico3>li>a')

    ullist =
    for i in ullist:
      if '/meinv/' in i:
            urllist.append(i)
    return urllist


def getpage(imglist):
    for l in imglist:
      headers = {
            "referer": "https://www.baidu.com/link?url=GgeDs1AzZQg7jAVgRWaaQVemNzUYNHFpN-PiFmUIyUHeaMQeoPb14_8g1oL7GmBggm70mm4e2EkM5F7lmQMUVq&wd=&eqid=fdcd73c000068a5900000004605ac987",
            "upgrade-insecure-requests": "1",
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0"
      }
      R = requests.get(f"https://www.tupianzj.com{l}", headers=headers).content.decode('gbk')
      imgsoup = BeautifulSoup(R, 'lxml').select('.pages > ul:nth-child(1) > li:nth-last-child(2)>a').text
      for i in range(1, int(imgsoup) + 1):
            if i == 1:
                imgurl = BeautifulSoup(R, 'lxml').select('#bigpicimg').get('src')
                tittle = BeautifulSoup(R, 'lxml').select('div.list_con:nth-child(3) > h1:nth-child(1)').text
                with open(tittle + '.' + imgurl.split('.')[-1], 'wb') as f:
                  f.write(requests.get(imgurl, headers=headers).content)
                  f.close()
                print(tittle + "         保存成功！")
            else:
                imgurl = 'https://www.tupianzj.com' + l.replace('.html', '') + f'_{i}.html'
                req=requests.get(imgurl,headers=headers).content.decode('gbk')
                u=BeautifulSoup(req, 'lxml').select('#bigpicimg').get('src')
                tittle = BeautifulSoup(req, 'lxml').select('div.list_con:nth-child(3) > h1:nth-child(1)').text
                with open(tittle + '.' + u.split('.')[-1], 'wb') as f:
                  f.write(requests.get(u, headers=headers).content)
                  f.close()
                print(tittle+"         保存成功！")


if __name__ == '__main__':
    listur = getUrl()
    getpage(listur)import requests
from bs4 import BeautifulSoup


def getUrl():
    headers = {
      "referer": "https://www.baidu.com/link?url=GgeDs1AzZQg7jAVgRWaaQVemNzUYNHFpN-PiFmUIyUHeaMQeoPb14_8g1oL7GmBggm70mm4e2EkM5F7lmQMUVq&wd=&eqid=fdcd73c000068a5900000004605ac987",
      "upgrade-insecure-requests": "1",
      "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0"
    }
    url = 'https://www.tupianzj.com/meinv/mm/nkmv/'

    urllist = []
    H = requests.get(url, headers=headers).text

    soup = BeautifulSoup(H, 'lxml').select('ul.d1.ico3>li>a')

    ullist =
    for i in ullist:
      if '/meinv/' in i:
            urllist.append(i)
    return urllist


def getpage(imglist):
    for l in imglist:
      headers = {
            "referer": "https://www.baidu.com/link?url=GgeDs1AzZQg7jAVgRWaaQVemNzUYNHFpN-PiFmUIyUHeaMQeoPb14_8g1oL7GmBggm70mm4e2EkM5F7lmQMUVq&wd=&eqid=fdcd73c000068a5900000004605ac987",
            "upgrade-insecure-requests": "1",
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0"
      }
      R = requests.get(f"https://www.tupianzj.com{l}", headers=headers).content.decode('gbk')
      imgsoup = BeautifulSoup(R, 'lxml').select('.pages > ul:nth-child(1) > li:nth-last-child(2)>a').text
      for i in range(1, int(imgsoup) + 1):
            if i == 1:
                imgurl = BeautifulSoup(R, 'lxml').select('#bigpicimg').get('src')
                tittle = BeautifulSoup(R, 'lxml').select('div.list_con:nth-child(3) > h1:nth-child(1)').text
                with open(tittle + '.' + imgurl.split('.')[-1], 'wb') as f:
                  f.write(requests.get(imgurl, headers=headers).content)
                  f.close()
                print(tittle + "         保存成功！")
            else:
                imgurl = 'https://www.tupianzj.com' + l.replace('.html', '') + f'_{i}.html'
                req=requests.get(imgurl,headers=headers).content.decode('gbk')
                u=BeautifulSoup(req, 'lxml').select('#bigpicimg').get('src')
                tittle = BeautifulSoup(req, 'lxml').select('div.list_con:nth-child(3) > h1:nth-child(1)').text
                with open(tittle + '.' + u.split('.')[-1], 'wb') as f:
                  f.write(requests.get(u, headers=headers).content)
                  f.close()
                print(tittle+"         保存成功！")


if __name__ == '__main__':
    listur = getUrl()
    getpage(listur)
页: 1 2 3 4 5 6 7 8 [9] 10 11 12 13 14 15
查看完整版本: BMW车载HiFi至尊女声天碟