[已解决]爬百度贴吧图片,为啥只生成一个文件夹

起风了番茄

import urllib.request
import re
import os
def open_url(url):
    req =urllib.request.Request(url)
    req.add_header('User-Agent',' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')
    return html

def get_img(html):
    p = r'<img class="BDE_Image".*?src="([^"]*\.jpg)".*?>'
    imglist = re.findall(p,html)

    try:
        os.mkdir('NewPics')
    except FileExistsError:
        pass
    os.chdir("NewPics")
    for each in imglist:
        filename = each.split("/")[-1]
        urllib.request.urlretrieve(each,filename,None)

if __name__ == '__main__':
    url = 'https://tieba.baidu.com/p/7766911770'
    get_img(open_url(url))

最佳答案

月排行榜 / 总排行榜

isdkz

2022-3-24 18:59:38

正则表达式不对：

import urllib.request
import re
import os
def open_url(url):
    req =urllib.request.Request(url)
    req.add_header('User-Agent',' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')
    return html

def get_img(html):
    p = r'<img class="BDE_Image".*?src="([^"]*\.jpg)[^"]*".*?>'        # 修改了正则表达式
    imglist = re.findall(p,html)

    try:
        os.mkdir('NewPics')
    except FileExistsError:
        pass
    os.chdir("NewPics")
    for each in imglist:
        filename = each.split("/")[-1]
        urllib.request.urlretrieve(each,filename,None)

if __name__ == '__main__':
    url = 'https://tieba.baidu.com/p/7766911770'
    get_img(open_url(url))

跳转到最佳答案楼层

isdkz

正则表达式不对：

import urllib.request
import re
import os
def open_url(url):
    req =urllib.request.Request(url)
    req.add_header('User-Agent',' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')
    return html

def get_img(html):
    p = r'<img class="BDE_Image".*?src="([^"]*\.jpg)[^"]*".*?>'        # 修改了正则表达式
    imglist = re.findall(p,html)

    try:
        os.mkdir('NewPics')
    except FileExistsError:
        pass
    os.chdir("NewPics")
    for each in imglist:
        filename = each.split("/")[-1]
        urllib.request.urlretrieve(each,filename,None)

if __name__ == '__main__':
    url = 'https://tieba.baidu.com/p/7766911770'
    get_img(open_url(url))

起风了番茄

isdkz 发表于 2022-3-24 18:59
正则表达式不对：

老哥我那个悬赏是跟这个题一样的,你能去答一下,悬赏结算给你吗?

isdkz

起风了番茄 发表于 2022-3-24 19:19
老哥我那个悬赏是跟这个题一样的,你能去答一下,悬赏结算给你吗?

那谢谢啦！