说明两点问题：
（一）.留言里有人评论说用XPath下载的图片打不开，其原因是定义的下载函数保存路径后缀名为'.jpg'，但是用XPath下载获得的图片url为'https://img3.doubanio.com/view/celebrity/s_ratio_celebrity/public/p616.webp'，本身图片为webp格式，所以若保存为jpg格式，肯定是打不开的。
(二). 老师在文章内讲的用XPath下载代码只能下载第一页的内容，并不是全部的数据，不知道大家有没有查看用xpath函数获得的数组，大家留言里的代码似乎和老师的一样，只能得到首页的内容，所以也是需要模拟翻页操作才能获得完整的数据。

以下是课后练习题：爬取宫崎骏的电影海报， Python3.6 IDLE
>>> import json
>>> import requests as req
>>> from lxml import etree
>>> from selenium import webdriver
>>> import os
>>> request_url = 'https://movie.douban.com/subject_search?search_text=宫崎骏&cat=1002'
>>> src_xpath = "//div[@class='item-root']/a[@class='cover-link']/img[@class='cover']/@src"
>>> title_xpath = "//div[@class='item-root']/div[@class='detail']/div[@class='title']/a[@class='title-text']"
>>> driver = webdriver.Chrome('/Users/apple/Downloads/chromedriver')
>>> driver.get(request_url)
>>> html = etree.HTML(driver.page_source)
>>> srcs = html.xpath(src_xpath)
>>> print (srcs) #大家可要看下打印出来的数据是否只是一页的内容，以及图片url的后缀格式
>>> picpath = '/Users/apple/Downloads/宫崎骏电影海报'
>>> if not os.path.isdir(picpath):
    os.mkdir(picpath)
>>> def download(src, id):
    dic = picpath + '/' + str(id) + '.webp'
    try:
        pic = req.get(src, timeout = 30)
        fp = open(dic, 'wb')
        fp.write(pic.content)
        fp.close()
    except req.exceptions.ConnectionError:
        print ('图片无法下载')
>>> for i in range(0, 150, 15):
    url = request_url + '&start=' + str(i)
    driver.get(url)
    html = etree.HTML(driver.page_source)
    srcs = html.xpath(src_xpath)
    titles = html.xpath(title_xpath)
    for src,title in zip(srcs, titles):
        download(src, title.text)

#环境：Mac Python3
#pip install selenium
#下载chromedriver，放到项目路径下（https://npm.taobao.org/mirrors/chromedriver/2.33/）
# coding:utf-8
import requests
import json
import os
from lxml import etree
from selenium import webdriver

query = '张柏芝'
downloadPath = '/Users/yong/Desktop/Python/xpath/images/'

''' 下载图片 '''
def download(src, id):
    dir = downloadPath + str(id) + '.jpg'
    try:
        pic = requests.get(src, timeout=10)
    except requests.exceptions.ConnectionError:
    # print 'error, %d 当前图片无法下载', %id
        print('图片无法下载')
    if not os.path.exists(downloadPath):
        os.mkdir(downloadPath)
    if os.path.exists(dir):
        print('已存在:'+ id)
        return
    fp = open(dir, 'wb')
    fp.write(pic.content)
    fp.close()
 
def searchImages():
    ''' for 循环 请求全部的 url '''
    for i in range(0, 22471, 20):
        url = 'https://www.douban.com/j/search_photo?q='+query+'&limit=20&start='+str(i)
        html = requests.get(url).text # 得到返回结果
        print('html:'+html)
        response = json.loads(html,encoding='utf-8') # 将 JSON 格式转换成 Python 对象
        for image in response['images']:
            print(image['src']) # 查看当前下载的图片网址
            download(image['src'], image['id']) # 下载一张图片

def getMovieImages():
    url = 'https://movie.douban.com/subject_search?search_text='+ query +'&cat=1002'
    driver = webdriver.Chrome('/Users/yong/Desktop/Python/xpath/libs/chromedriver')
    driver.get(url)
    html = etree.HTML(driver.page_source)
    # 使用xpath helper, ctrl+shit+x 选中元素，如果要匹配全部，则需要修改query 表达式
    src_xpath = "//div[@class='item-root']/a[@class='cover-link']/img[@class='cover']/@src"
    title_xpath = "//div[@class='item-root']/div[@class='detail']/div[@class='title']/a[@class='title-text']"

    srcs = html.xpath(src_xpath)
    titles = html.xpath(title_xpath)
    for src, title in zip(srcs, titles):
        print('\t'.join([str(src),str(title.text)]))
        download(src, title.text)

    driver.close()

getMovieImages()

老师您好，我根据您的代码修改了一下，主要是添加了一个图片的目录，然后是下载大图。这里的大图是因为 /photo/thumb/public/ 这样的链接下载的图片是缩略图，只有把 thumb 替换成 l 之后下载的图片才是相对来说的大图。replace 方法和 re 中的 sub 方法都能实现替换，我的疑问是哪个实现起来更高速一点呢？提前感谢老师，我写的代码在下面~

# coding:utf-8
import requests
import json
import re
import os

query = '王祖贤'
path = os.getcwd() # 当前路径，可以替换成别的路径
picpath = path + '/' + query # 设置的图片目录
print(picpath) # 输出设置的图片目录
if not os.path.isdir(picpath): # 如果图片目录未创建则创建一个
    os.mkdir(picpath)


def download(src, id):
    dir = picpath + '/' + str(id) + '.jpg'
    try:
        pic = requests.get(src, timeout=10)
    except requests.exceptions.ConnectionError:
        # print 'error, %d 当前图片无法下载', %id
        print('图片无法下载')
    fp = open(dir, 'wb')
    fp.write(pic.content)
    fp.close()


''' for 循环 请求全部的 url '''
for i in range(0, 22471, 20): #
    url = 'https://www.douban.com/j/search_photo?q=' + query + '&limit=20&start=' + str(i)
    html = requests.get(url).text # 得到返回结果
    response = json.loads(html, encoding='utf-8') # 将 JSON 格式转换成 Python 对象
    print('已下载 ' + str(i) + ' 张图片')
    for image in response['images']:
        image['src'] = image['src'].replace('thumb', 'l')
        # image['src'] = re.sub(r'thumb', r'l', image['src'])
        print(image['src']) # 查看当前下载的图片网址
        download(image['src'], image['id']) # 下载一张图片

https://github.com/qinggeouye/GeekTime/blob/master/DataAnalysis/10_crawl_xpath.py

import os
import requests
from lxml import etree
from selenium import webdriver

search_text = '王祖贤'
start = 0 # 请求 url 的 start 从 0 开始，每一页间隔 15，有 6 页
total = 90
limit = 15

# 电影海报图片地址
src_xpath = "//div[@class='item-root']/a[@class='cover-link']/img[@class='cover']/@src"
# 电影海报图片title
title_xpath = "//div[@class='item-root']/div[@class='detail']/div[@class='title']/a[@class='title-text']"

# 保存目录
pic_path = '10/xpath' # 相对目录
# WebDriver 创建一个 Chrome 浏览器的 drive
driver = webdriver.Chrome('./chromedriver') # MAC 版本


# 创建图片保存路径
def mk_save_path(pic_path_):
    if not os.path.exists(pic_path_):
        os.makedirs(pic_path_)
    return os.getcwd() + '/' + pic_path_ + '/'


# 下载图片
def download(src, pic_id, save_path_):
    directory = save_path_ + str(pic_id) + '.jpg'
    try:
        pic = requests.get(src, timeout=10)
        fp = open(directory, 'wb')
        fp.write(pic.content)
        fp.close()
    except requests.exceptions.ConnectionError:
        print('图片如无法下载')


def get_response_xpath():
    save_path = mk_save_path(pic_path)
    for i in range(start, total, limit):
        requests_url = 'https://search.douban.com/movie/subject_search?search_text=' + search_text + '&cat=1002' + \
                       '&start=' + str(i)
        driver.get(url=requests_url)
        html = etree.HTML(driver.page_source)
        src_list = html.xpath(src_xpath)
        title_list = html.xpath(title_xpath)
        for src, title in zip(src_list, title_list):
            download(src, title.text, save_path)


if __name__ == '__main__':
    get_response_xpath()

https://github.com/qinggeouye/GeekTime/blob/master/DataAnalysis/10_crawl.py

# coding: utf-8
import os

import requests
import json


# 下载图片
def download(src, pic_id, save_path_):
    directory = save_path_ + str(pic_id) + '.jpg'

    try:
        pic = requests.get(src, timeout=10)
        fp = open(directory, 'wb')
        fp.write(pic.content)
        fp.close()
    except requests.exceptions.ConnectionError:
        print('图片如无法下载')


# 获取返回页面内容
def get_resp(query_, limit_, start_):
    url_ = 'https://www.douban.com/j/search_photo?q=' + query_ + '&limit=' + str(limit_) + '&start=' + str(start_)
    html_ = requests.get(url_).text # 得到返回结果
    response_ = json.loads(html_, encoding='utf-8') # 将 JSON 格式转换为 Python 对象
    return response_


query = '王祖贤'
limit = 20
start = 0

''' 获取图片总数量 '''
total = get_resp(query, limit, start)['total']
print(total)

pic_path = '10' # 相对目录
if not os.path.exists(pic_path):
    os.mkdir(pic_path)
save_path = os.getcwd() + '/' + pic_path + '/'

# 循环 请求全部的 url
for i in range(start, total, limit):
    response = get_resp(query, limit, i)
    for image in response['images']:
        print(image['src']) # 查看当前下载的图片地址
        download(image['src'], image['id'], save_path) # 下载一张图片

网址：豆瓣电影；任务：批量下载赵丽颖电影海报（支持翻页，自定义终止下载量）；python3.X；
浏览器：Google Chrome ；唯一要注意的是webdriver的路径。全都是这门课程里面的知识点
# -*- coding: utf-8 -*-
import requests
from lxml import etree
from selenium import webdriver
import os

name = '赵丽颖'

def download(src, id):
    if not os.path.isdir("Xpath的翻页图片包"):
        os.mkdir("Xpath的翻页图片包")
    dir = os.path.join("Xpath的翻页图片包/", str(id) + '.webp')
    try:
        pic = requests.get(src, timeout = 10)
        with open(dir, 'wb') as d:
            d.write(pic.content)
    except requests.exceptions.ConnectionError:
        print("图片无法下载")

def down_load(request_url):
    driver.get(request_url)
    html = etree.HTML(driver.page_source)
    src_xpath = "//div[@class='item-root']/a[@class='cover-link']/img[@class='cover']/@src"
    title_xpath = "//div[@class='item-root']/div[@class='detail']/div[@class='title']/a[@class='title-text']"
    srcs = html.xpath(src_xpath)


    titles = html.xpath(title_xpath)
    num = len(srcs)
    if num > 15:
        srcs = srcs[1:]
        titles = titles[1:]

    for src, title in zip(srcs, titles):
        if title is None:
            continue
        print(src)
        download(src, title.text)
    print('OK')
    print(num)
    if num >= 1:
        return True
    else:
        return False

if __name__ == '__main__':
    requests_url = "https://movie.douban.com/subject_search?search_text=" + name
    driver = webdriver.Chrome(executable_path=r'C:\Users\XXX\AppData\Local\Google\Chrome\Application\chromedriver.exe')
    driver.get(requests_url)
    html = etree.HTML(driver.page_source)
    print(html)

    base_url = 'https://movie.douban.com/subject_search?search_text=' + name + '&cat=1002&start='
    start = 0
    while start < 70:
        request_url = base_url + str(start)
        flag = down_load(request_url)
        if flag:
            start += 15
        else:
            break
    print("结束")

练习内容：使用 XPath 下载宫崎骏相关的电影海报！！！

源码如下：
''' To download all pages '''

### use webdriver to simulate page loading
from selenium import webdriver
import requests
from lxml import etree
import pyprind
import time
import re

def download_pics(src, p_id):
    ''' 下载指定图片 '''
    
    save_dir = 'pics/'
    if isinstance(p_id, str):
        # 过滤非法的文件名符号
        p_id = re.sub(r'[\\/:?|*]+', ' ', p_id)
        save_dir += p_id + '.jpg'
    else:
        save_dir += str(p_id) + '.jpg'
    try:
        pic = requests.get(src, timeout=10)
        with open(save_dir, 'wb') as fout:
            fout.write(pic.content)
    except requests.exceptions.ConnectionError:
        print('无法连接到图片 %d' % p_id)

    return True

request_url = "https://movie.douban.com/subject_search?search_text=%E5%AE%AB%E5%B4%8E%E9%AA%8F&cat=1002"
driver = webdriver.Chrome()

# 通过观察不同页码下的网页地址，大概有140个搜索结果
for i in range(0, 136, 15):
    driver.get(request_url + "&start=" + str(i))
    driver.implicitly_wait(10)
    # 一个小小的防被封 IP 措施
    time.sleep(3)

    html = driver.execute_script("return document.documentElement.outerHTML")
    # html = requests.get(request_url).text
    html = etree.HTML(html)

    src_xpath = "//div[@class='item-root']/a/img/@src"
    title_xpath = "//div/div/div/a[@class='title-text']"
    srcs = html.xpath(src_xpath)
    titles = html.xpath(title_xpath)

    # 一个用来显示进度百分数的包
    pper = pyprind.ProgPercent(len(srcs))
    for src, title in zip(srcs, titles):
        download_pics(src, title.text)
        pper.update()