爬图片

根据txt爬图片

import os
from icrawler.builtin import BingImageCrawler
path = r'D:\pycharm_1\Image'
f = open('starName.txt', 'r')
lines = f.readlines()
i=18
for i, line in enumerate(lines):
    if i>25:
        break
    if i==1:
        continue

    name = line.strip('\n')
    file_path = os.path.join(path, name)
   # if not os.path.exists(file_path):
    #    os.makedirs(file_path)
    bing_storage = {'root_dir': file_path}
    bing_crawler = BingImageCrawler(parser_threads=2, downloader_threads=4, storage=bing_storage)
    bing_crawler.crawl(keyword=name,max_num=50)
    print('第{}位明星：{}'.format(i, name))

进入网站根据名字爬图片

import requests
import re
import os
from pypinyin import pinyin, lazy_pinyin

def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print("")


def getPageUrls(text, name):
    re_pageUrl = r'href="(.+)">\s*<img src="(.+)" alt="' + name
    return re.findall(re_pageUrl, text)


def downPictures(text, root, name):
    pageUrls = getPageUrls(text, name)
    titles = re.findall(r'alt="' + name + r'(.+)" ', text)
    for i in range(len(pageUrls)):
        pageUrl = pageUrls[i][0]
        path = root + titles[i] + "//"
        if not os.path.exists(path):
            os.mkdir(path)
        if not os.listdir(path):
            pageText = getHTMLText(pageUrl)
            totalPics = int(re.findall(r'<em>(.+)</em>）', pageText)[0])
            downUrl = re.findall(r'href="(.+?)" class="">下载图片', pageText)[0]
            cnt = 1;
            while (cnt <= totalPics):
                picPath = path + str(cnt) + ".jpg"
                r = requests.get(downUrl)
                with open(picPath, 'wb') as f:
                    f.write(r.content)
                    f.close()
                print('{} - 第{}张下载已完成\n'.format(titles[i], cnt))
                cnt += 1
                nextPageUrl = re.findall(r'href="(.+?)">下一张', pageText)[0]
                pageText = getHTMLText(nextPageUrl)
                downUrl = re.findall(r'href="(.+?)" class="">下载图片', pageText)[0]
    return


def main():
    name = input("请输入你喜欢的明星的名字:")
    nameUrl = "http://www.win4000.com/mt/" + ''.join(lazy_pinyin(name)) + ".html"
    try:
        text = getHTMLText(nameUrl)
        if not re.findall(r'暂无(.+)!', text):
            root = "D://pycharm//" + name + "//"
            if not os.path.exists(root):
                os.mkdir(root)
            downPictures(text, root, name)
            try:
                nextPage = re.findall(r'next" href="(.+)"', text)[0]
                while (nextPage):
                    nextText = getHTMLText(nextPage)
                    downPictures(nextText, root, name)
                    nextPage = re.findall(r'next" href="(.+)"', nextText)[0]
            except IndexError:
                print("已全部下载完毕")
    except TypeError:
        print("不好意思，没有{}的照片".format(name))
    return


if __name__ == '__main__':
    main()