正在争鋒 2023-01-06 15:38 采纳率: 50%
浏览 83
已结题

用python爬虫始终报FileNotFoundErro: [Errno 2] No such file or directory

用以下代码爬取网页时,都可以获取到数据,图片url都能全部获取到

就是直到,目录创建这一块,无论使用是用绝对路径还是相对路径,都会报错FileNotFoundErro### r: [Errno 2] No such file or directory

请问这是怎么回事?

from  urllib.request import urlretrieve
import requests
import os
from bs4 import BeautifulSoup
import time
import random
headers_list = [
    {
        'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 8.0.0; SM-G955U Build/R16NW) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 10; SM-G981B) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (iPad; CPU OS 13_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) CriOS/87.0.4280.77 Mobile/15E148 Safari/604.1'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.109 Safari/537.36 CrKey/1.54.248666'
    }, {
        'user-agent': 'Mozilla/5.0 (X11; Linux aarch64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.188 Safari/537.36 CrKey/1.54.250320'
    }, {
        'user-agent': 'Mozilla/5.0 (BB10; Touch) AppleWebKit/537.10+ (KHTML, like Gecko) Version/10.0.9.2372 Mobile Safari/537.10+'
    }, {
        'user-agent': 'Mozilla/5.0 (PlayBook; U; RIM Tablet OS 2.1.0; en-US) AppleWebKit/536.2+ (KHTML like Gecko) Version/7.2.1.0 Safari/536.2+'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; U; Android 4.3; en-us; SM-N900T Build/JSS15J) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; U; Android 4.1; en-us; GT-N7100 Build/JRO03C) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; U; Android 4.0; en-us; GT-I9300 Build/IMM76D) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 7.0; SM-G950U Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.84 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 8.0.0; SM-G965U Build/R16NW) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.111 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 8.1.0; SM-T837A) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.80 Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; U; en-us; KFAPWI Build/JDQ39) AppleWebKit/535.19 (KHTML, like Gecko) Silk/3.13 Safari/535.19 Silk-Accelerated=true'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; U; Android 4.4.2; en-us; LGMS323 Build/KOT49I.MS32310c) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Windows Phone 10.0; Android 4.2.1; Microsoft; Lumia 550) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2486.0 Mobile Safari/537.36 Edge/14.14263'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 6.0.1; Moto G (4)) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 6.0.1; Nexus 10 Build/MOB31T) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 8.0.0; Nexus 5X Build/OPR4.170623.006) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 7.1.1; Nexus 6 Build/N6F26U) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 8.0.0; Nexus 6P Build/OPP3.170518.006) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 6.0.1; Nexus 7 Build/MOB30X) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (compatible; MSIE 10.0; Windows Phone 8.0; Trident/6.0; IEMobile/10.0; ARM; Touch; NOKIA; Lumia 520)'
    }, {
        'user-agent': 'Mozilla/5.0 (MeeGo; NokiaN9) AppleWebKit/534.13 (KHTML, like Gecko) NokiaBrowser/8.5.0 Mobile Safari/534.13'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 9; Pixel 3 Build/PQ1A.181105.017.A1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.158 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 10; Pixel 4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 11; Pixel 3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.181 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 5.0; SM-G900P Build/LRX21T) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (Linux; Android 8.0.0; Pixel 2 XL Build/OPD1.170816.004) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Mobile Safari/537.36'
    }, {
        'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 10_3_1 like Mac OS X) AppleWebKit/603.1.30 (KHTML, like Gecko) Version/10.0 Mobile/14E304 Safari/602.1'
    }, {
        'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1'
    }, {
        'user-agent': 'Mozilla/5.0 (iPad; CPU OS 11_0 like Mac OS X) AppleWebKit/604.1.34 (KHTML, like Gecko) Version/11.0 Mobile/15A5341f Safari/604.1'
    }
]

headers = random.choice(headers_list)
url = "https://www.doutuwang.com/category/dashijian/page/1"
html = requests.get(url,headers).content.decode("utf-8")
soup = BeautifulSoup(html,"lxml")
doutu_web_li_list = soup.find_all("li",class_="post box row fixed-hight")

# print(len(doutu_web_list))




# 爬取一页的链接
doutu_href_list = []
for doutu_web_li in doutu_web_li_list:
    doutu_name = doutu_web_li.a.get("title")
    doutu_web = doutu_web_li.a.get("href")
    doutu_list = doutu_name + "=" + doutu_web
    doutu_href_list.append(doutu_list)
# print(doutu_href_list)
flag = 0
for doutu_href in doutu_href_list:
    print(doutu_href)
    doutu_href = doutu_href.split("=")
    pic_dir_name = doutu_href[0]
    pic_dir_path = "doutu集合"
    doutu_url = doutu_href[1]
    html_pic = requests.get(doutu_url,headers=headers).content.decode("utf-8")
    soup = BeautifulSoup(html_pic,'lxml')
    div_tag = soup.find("div",id="post_content")
    # print(len(div_tag.find_all("p")))       # 列举每个html_pic的图片个数
    all_pic = div_tag.find_all("p")
    # print(all_pic)
    for each_pic in all_pic:
        # print(each_pic.a)
        flag += 1
        pic_name = f'{str(flag)}.jpg'
        try:
            each_pic_url = each_pic.a.get("href")
        except AttributeError as e:
            print(e)
            continue      
        print(pic_name)
        print(each_pic_url)
        
        # 以下问题的代码

        if pic_dir_path not in os.listdir():
            os.mkdir(pic_dir_path)
        if pic_dir_name not in os.listdir("doutu集合"):
            os.chdir(pic_dir_path)   # 进入doutu集合下才创建  次目录/
            print(os.getcwd())
            os.mkdir(pic_dir_name)
            os.chdir("..")  # 目录要指定回当前
            print(os.getcwd())

        filename = os.path.join(pic_dir_path,pic_dir_name)
        print(filename)
        print(os.getcwd())
        # # time.sleep(2)

        urlretrieve(each_pic_url,filename=os.getcwd()+"\\"+filename+"\\"+pic_name)
        print(os.getcwd()+"\\"+filename+"\\"+pic_name)
        # time.sleep(2)



"""

以下的报错问题

FileNotFoundError: [Errno 2] No such file or directory
urllib.error.URLError: <urlopen error [Errno 2] No such file or directory>
"""

  • 写回答

4条回答 默认 最新

  • CSDN专家-showbo 2023-01-06 17:13
    关注

    我是运行到这里出问题,url中包含中文urlretrieve出错了,要对中文进行编码

    img


    改下面这里编码下url就正常了。

            try:
                each_pic_url = each_pic.a.get("href")
            except AttributeError as e:
                print(e)
                continue  
            ###############
            each_pic_url = quote(each_pic_url).replace('https%3A//','https://')##编码下网址,注意:也会被编码,要替换回来
            ###############
            print(pic_name)
            print(each_pic_url)
    
    本回答被题主选为最佳回答 , 对您是否有帮助呢?
    评论
查看更多回答(3条)

报告相同问题?

问题事件

  • 系统已结题 1月14日
  • 已采纳回答 1月6日
  • 创建了问题 1月6日

悬赏问题

  • ¥15 求jacquard数据集
  • ¥15 w10部分软件不能联网
  • ¥15 关于安装hbase的问题(操作系统-windows)
  • ¥15 cadence617版本,如何做一个参数可调的反相器
  • ¥15 novnc连接pve虚拟机报错安全协议不支持262
  • ¥15 设备精度0.03给多少公差能达到CPK1.33
  • ¥15 qt+ffmpeg报错non-existing PPS 0 referenced
  • ¥15 FOC simulink
  • ¥50 MacOS 使用虚拟机安装k8s
  • ¥20 玩游戏gpu和cpu利用率特别低,玩游戏卡顿