Python爬取知乎图片

from bs4 import BeautifulSoup
from selenium import webdriver
import time
import urllib.request
import html.parser
import ssl

ssl._create_default_https_context = ssl._create_unverified_context


def main():
    # ***************** 调用浏览器打开网址 *******************************
    driver = webdriver.Safari()

    # URL
    driver.get('https://www.zhihu.com/question/292901966/answer/800705040')  # 01新垣结衣
    driver.get("https://www.zhihu.com/question/35931586") # 02你的日常搭配是什么样子？
    driver.get("https://www.zhihu.com/question/61235373")  # 03女生腿好看胸平是一种什么体验？
    driver.get("https://www.zhihu.com/question/28481779")  # 04腿长是一种什么体验？
    driver.get("https://www.zhihu.com/question/19671417") # 05拍照时怎样摆姿势好看？
    driver.get("https://www.zhihu.com/question/20196263") # 06女性胸部过大会有哪些困扰与不便？
    driver.get("https://www.zhihu.com/question/46458423") # 07短发女孩要怎么拍照才性感？
    driver.get("https://www.zhihu.com/question/26037846")  # 08身材好是一种怎样的体验？
    driver.get("https://www.zhihu.com/question/333026642/answer/780949078")  # 09

    def execute_times(times):
        # ***************** 滚动界面,点击更多按钮 ***************************
        for n in range(times):
            driver.execute_script('window.scrollTo(0, document.body.scrollHeight);')  # 滑动到浏览器底部
            time.sleep(2)  # 等待加载
            try:
                driver.find_element_by_css_selector('button.QuestionMainAction').click()  # 点击更多按钮
                print('Page' + str(n))  # 输出页码数
                time.sleep(1)
            except:
                break

    execute_times(5000)

    # ************ 存储网页,⽤beautifulSoup把压缩后的 HTML ⽂件结构化并保存 ************
    result_raw = driver.page_source  # 原始网页
    result_soup = BeautifulSoup(result_raw, 'html.parser')
    result_bf = result_soup.prettify()  # 结构化原 HTML 文件

    with open('./output/rawfile/raw_result.txt', 'w') as girls:
        girls.write(result_bf)
    girls.close()
    print('HTML数据存储成功!')

    # ************ 解码<noscript> html.parser.unescape ************
    with open('./output/rawfile/noscript_meta.txt', 'w') as noscript_meta:
        noscript_nodes = result_soup.find_all('noscript')  # 找到所有<noscript>node
        noscript_inner_all = ''
        for noscript in noscript_nodes:
            noscript_inner = noscript.get_text()  # 获取<noscript> node内容
            noscript_inner_all += noscript_inner + '\n'

        noscript_all = html.parser.unescape(noscript_inner_all)  # 将内容转码并存储
        noscript_meta.write(noscript_all)
    noscript_meta.close()
    print('转码后<noscript>成功!')

    # ************************ 下载图片 ****************************
    img_soup = BeautifulSoup(noscript_all, 'html.parser')
    img_nodes = img_soup.find_all('img')
    with open("./output/rawfile/img_meta.txt", 'w') as img_meta:
        count = 0
        for img in img_nodes:
            if img.get('src') is not None:
                img_url = img.get('src')

                line = str(count) + "\t" + img_url + "\n"
                img_meta.write(line)
                urllib.request.urlretrieve(img_url, "./output/image/output0/" + str(count) + ".jpg")  # 一个一个下载图片
                count += 1

    img_meta.close()
    print("下载成功!")


if __name__ == '__main__':
    main()