Use python reptiles crawl URLs from a given picture and download it to a custom folder

# encoding=gbk

import re
import urllib
import os
import requests

def get_onepage_urls(onepageurl):
    if not onepageurl:
        print('执行结束')
        return [], ''
    try:
        html = requests.get(onepageurl).text
    except Exception as e:
        print(e)
        pic_urls = []
        fanye_url = ''
        return pic_urls, fanye_url
    pic_urls = re.findall('"objURL":"(.*?)",', html, re.S)
    html = requests.get(onepageurl)
    html.encoding = 'utf-8'
    content = html.text
    fanye_urls = re.findall(re.compile(r'<a href="(.*)" class="n">下一页</a>'), content, flags=0)
    fanye_url = 'http://image.baidu.com' + fanye_urls[0] if fanye_urls else ''
    return pic_urls, fanye_url

def down_pic(pic_urls, localPath):
    if not os.path.exists(localPath):  # 新建文件夹
        os.mkdir(localPath)
    """给出图片链接列表, 下载图片"""
    for i, pic_url in enumerate(pic_urls):
        try:
            pic = requests.get(pic_url, timeout=15)
            string = str(i + 1) + '.jpg'
            with open(localPath + '%d.jpg' % i, 'wb')as f:
                f.write(pic.content)
                print('成功下载第%s张图片: %s' % (str(i + 1), str(pic_url)))
        except Exception as e:
            print('下载第%s张图片时失败: %s' % (str(i + 1), str(pic_url)))
            print(e)
            continue

if __name__ == '__main__':
    keyword = '鸣人'  # 关键词, 改为你想输入的词即可, 相当于在百度图片里搜索一样
    url_init_first = r'http://image.baidu.com/search/index?tn=baiduimage&word= keyword'
    url_init = url_init_first + urllib.parse.quote(keyword, safe='/')
    all_pic_urls = []
    onepage_urls, fanye_url = get_onepage_urls(url_init)
    all_pic_urls.extend(onepage_urls)

    fanye_count = 1  # 图片所在页数，下载完后调整这里就行
    while 1:
        onepage_urls, fanye_url = get_onepage_urls(fanye_url)
        fanye_count += 1
        print('第%s页' % fanye_count)
        if fanye_url == '' and onepage_urls == []:
            break
        all_pic_urls.extend(onepage_urls)

    down_pic(list(set(all_pic_urls)), r'F:\爬取图片\\')  # 保存位置也可以修改