[已解决]python爬虫爬取套图保存问题

小小蛙

如题，已经获取到每张图片的链接与标题，怎么保存到本地文件夹，我的是错的

import urllib.request
import re
import os
from bs4 import BeautifulSoup
def request_url():
    url='https://www.tooopen.com/topiclist/9620.aspx'
    response =urllib.request.Request(url)
    html = urllib.request.urlopen(response)
    #html.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36')

    html = html.read().decode('utf-8')
    reg =r'<a class="pic" href="(.*?)" title="(.*?)" target="_blank">'
    photo_url= re.findall(reg,html)
    #print(photo_url[0][0])
    for i in photo_url:
        #urls =i[0]
        #name =i[1]
        urls,name =i

    r =urllib.request.urlopen(urls).read().decode('utf-8')
    #print(r)
    soup =BeautifulSoup(r,"html.parser")
    img_url = soup.find("div",class_="img-list").find_all("a")


    
    reg=r'http(.*?)jpg'
    link = re.findall(reg,str(img_url))
    
    for i in link:
        i='http'+i+'jpg'
        print(i)
        download_imgs = urllib.request.urlopen(i).read()

        
        with open('.jpg','wb') as f:
            f.write(i)

        




request_url()

     

最佳答案

月排行榜 / 总排行榜

一个账号

2020-3-14 18:45:10

小小蛙 发表于 2020-3-14 18:39
版主好，我用pip安装requests模块一直会报错，可以用urllib模块演示吗

import urllib.request
import re
import os
import random
from bs4 import BeautifulSoup
def request_url():
    url='https://www.tooopen.com/topiclist/9620.aspx'
    response =urllib.request.Request(url)
    html = urllib.request.urlopen(response)
    #html.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36')

    html = html.read().decode('utf-8')
    reg =r'<a class="pic" href="(.*?)" title="(.*?)" target="_blank">'
    photo_url= re.findall(reg,html)
    #print(photo_url[0][0])
    for i in photo_url:
        #urls =i[0]
        #name =i[1]
        urls,name =i

    r =urllib.request.urlopen(urls).read().decode('utf-8')
    #print(r)
    soup =BeautifulSoup(r,"html.parser")
    img_url = soup.find("div",class_="img-list").find_all("a")


    
    reg=r'http(.*?)jpg'
    link = re.findall(reg,str(img_url))
    
    for i in link:
        i='http'+i+'jpg'
        print(i)
        download_imgs = urllib.request.urlopen(i).read()

        res = urllib.request.urlopen(i)
        data = res.read()

        
        with open(f'{random.randint(1, 1000)}.jpg','wb') as f:
            f.write(data)

        




request_url()

跳转到最佳答案楼层

wp231957

上一个帖子谁删的

小小蛙

wp231957 发表于 2020-3-14 18:34
上一个帖子谁删的

一位版主大哥

一个账号

代码帮楼主改好了：

import urllib.request
import re
import os
import random
import requests
from bs4 import BeautifulSoup
def request_url():
    url='https://www.tooopen.com/topiclist/9620.aspx'
    response =urllib.request.Request(url)
    html = urllib.request.urlopen(response)
    #html.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36')

    html = html.read().decode('utf-8')
    reg =r'<a class="pic" href="(.*?)" title="(.*?)" target="_blank">'
    photo_url= re.findall(reg,html)
    #print(photo_url[0][0])
    for i in photo_url:
        #urls =i[0]
        #name =i[1]
        urls,name =i

    r =urllib.request.urlopen(urls).read().decode('utf-8')
    #print(r)
    soup =BeautifulSoup(r,"html.parser")
    img_url = soup.find("div",class_="img-list").find_all("a")


    
    reg=r'http(.*?)jpg'
    link = re.findall(reg,str(img_url))
    
    for i in link:
        i='http'+i+'jpg'
        print(i)
        download_imgs = urllib.request.urlopen(i).read()

        res = requests.get(i)

        
        with open(f'{random.randint(1, 1000)}.jpg','wb') as f:
            f.write(res.content)

        




request_url()

     

小小蛙

一个账号 发表于 2020-3-14 18:36
我删的，怎么了？

我用pip安装requests模块一直会报错，可以用urllib模块演示吗

一个账号

小小蛙 发表于 2020-3-14 18:39
版主好，我用pip安装requests模块一直会报错，可以用urllib模块演示吗

import urllib.request
import re
import os
import random
from bs4 import BeautifulSoup
def request_url():
    url='https://www.tooopen.com/topiclist/9620.aspx'
    response =urllib.request.Request(url)
    html = urllib.request.urlopen(response)
    #html.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36')

    html = html.read().decode('utf-8')
    reg =r'<a class="pic" href="(.*?)" title="(.*?)" target="_blank">'
    photo_url= re.findall(reg,html)
    #print(photo_url[0][0])
    for i in photo_url:
        #urls =i[0]
        #name =i[1]
        urls,name =i

    r =urllib.request.urlopen(urls).read().decode('utf-8')
    #print(r)
    soup =BeautifulSoup(r,"html.parser")
    img_url = soup.find("div",class_="img-list").find_all("a")


    
    reg=r'http(.*?)jpg'
    link = re.findall(reg,str(img_url))
    
    for i in link:
        i='http'+i+'jpg'
        print(i)
        download_imgs = urllib.request.urlopen(i).read()

        res = urllib.request.urlopen(i)
        data = res.read()

        
        with open(f'{random.randint(1, 1000)}.jpg','wb') as f:
            f.write(data)

        




request_url()

小小蛙

一个账号 发表于 2020-3-14 18:45

老哥，可以把照片名字打印上去吗，已经提取到了上面那个name