python爬虫练习系列之三：下载某站文档资料

【目标】

下载某网站 https://www.pcac.org.cn/eportal/ui?pageId=595055

拟获取列表中文档数据。

先获取总页数，如下图：

然后逐步翻页获取每个页面链接。

有些链接指向.pdf文档，可以直接下载；有些链接指向html文件，直接保存；有些有一个附件，直接下载；有些有多个附件，建立目录后保存。

【优化细节】

若文件已经下载过，则自动跳过；

若获取某个文件下载出错，则自动跳过进行下一个下载。

【下载附件】推荐用requests库，好处是有错误状态码，且不用判断文件下载时间，且可以重命名文件，故不用driver.get(url)下载文件。

【示范代码】

import os
import time
from urllib import parse

import requests
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}


def mk_dir(dir1):
    if not os.path.exists(dir1):
        os.mkdir(dir1)


def file_exist(base_dir, pure_filename):
    if os.path.exists(os.path.join(base_dir, pure_filename)):
        return True
    return False

base_dir = os.path.join(os.getcwd(), 'download')
mk_dir(base_dir)


def write_html_page(browser, filename):
    browser.switch_to.window(browser.window_handles[-1])
    page = browser.page_source
    with open(filename, 'w', encoding='utf-8') as f:
        f.write(page)


print('-' * 70)
chrome_options = Options()
chrome_options.add_argument("--headless")  # 在后台运行

chrome_options.add_experimental_option("prefs", {
    "download.default_directory": base_dir,
  
})

driver = webdriver.Chrome(options=chrome_options, service=Service('./chromedriver.exe'))

base_url = 'https://www.pcac.org.cn/eportal/ui?pageId=595055'
driver.get(base_url)
time.sleep(1)
total_page = driver.find_element(By.XPATH, '//div[@class="easysite-total-page fy-div"]/span[1]/b[2]').text
# total_page=driver.find_element(By.XPATH,'//div[@class="easysite-total-page fy-div"]')
# 85篇文章 当前页:1/6  123456 下一页
print(f'最大页数为：{total_page}')

for i in range(1, int(total_page) + 1):

    url2 = f'https://www.pcac.org.cn/eportal/ui?pageId=595055&currentPage={i}&moduleId=b18e5af5da4f400fac1fd7ebf4a8bdd1&staticRequest=yes'
    driver.get(url2)

    li_list = driver.find_elements(By.XPATH, '//*[@id="b18e5af5da4f400fac1fd7ebf4a8bdd1"]/div[2]/ul/li')
    item_list = []
    for li in li_list:
        tag_a = li.find_element(By.TAG_NAME, 'a')
        title1 = tag_a.text
        link1 = tag_a.get_attribute('href')
        item_list.append((title1, link1))

    print('='*20+f'第{i}页，共有{len(item_list)}条记录'+'='*15)

    k = 1
    for item in item_list:
        print('>>' + '-' * 60)
        print(f'[第{i}页-{k}]-正在获取{item[1]}')
        if '.pdf' in item[1]:
            print(f'【直接获取】pdf文件：{item[1]}')
            # 直接下载url文件
            old_filename = item[1].split('/')[-1]
            old_filename = parse.unquote(old_filename)
            new_filename = item[0] + '.pdf'
            full_name = os.path.join(base_dir, new_filename)
            print(old_filename, new_filename)
            if file_exist(base_dir, new_filename):
                print(f'------跳过-->文件<{new_filename}>已下载...')
                k += 1
                continue

            try:
                r = requests.get(item[1], headers=headers)
                print(r.status_code)
                with open(full_name, 'wb') as f:
                    f.write(r.content)
            except:
                print(f'>>>except 下载发生错误,跳过{item[1]}')
            k += 1

        else:
            # 先打开二级页面

            driver.get(item[1])
            content = driver.find_element(By.XPATH, '//div[@class="xl-main"]')

            attach_list = content.find_elements(By.TAG_NAME, 'a')

            if not attach_list:  # 为html文件，无附件下载
                print('【单个html】网页内容，直接下载')
                fname=os.path.join(base_dir, driver.title + ".html")
                if os.path.exists(fname):
                    print(f'------跳过-->文件<{driver.title + ".html"}>已下载...')
                    k += 1
                    continue
                write_html_page(driver, f'{fname}')
                k += 1
                continue
            if len(attach_list) == 1:  # 单个文件下载，保存在当期目录
                a_tag = attach_list[0]
                item_dir = base_dir
                link3 = a_tag.get_attribute('href')
                old_filename = a_tag.get_attribute('href').split('/')[-1]
                old_filename = parse.unquote(old_filename)
                new_filename = a_tag.text
                new_full_filename = os.path.join(base_dir, new_filename)
                print('【单个文件】下载：', link3, old_filename, new_filename, new_full_filename)
                # if os.path.exists(os.path.join(item_dir, new_filename)):
                if file_exist(base_dir, new_filename):
                    print(f'------跳过-->文件<{new_filename}>已下载...')
                    k += 1
                    continue
                try:
                    r = requests.get(link3, headers=headers)
                    print(r.status_code)
                    with open(new_full_filename, 'wb') as f:
                        f.write(r.content)
                except:
                    print(f'>>>except 下载发生错误,跳过{link3}')

                k += 1

            else:
                # len(attach_list) > 1:   有多个附件需要下载，建立目录
                item_dir = os.path.join(base_dir, item[0])
                mk_dir(item_dir)
                print(f'【多附件下载】，附件个数：{len(attach_list)}')
                print('item_dir', item_dir)

                files = []
                for a_tag in attach_list:
                    # element = a_tag.get_attribute('outerHTML')
                    # print(element)
                    link3 = a_tag.get_attribute('href')
                    old_filename = a_tag.get_attribute('href').split('/')[-1]
                    old_filename = parse.unquote(old_filename)
                    new_filename = a_tag.text
                    full_filename = os.path.join(item_dir, new_filename)

                    print(link3, old_filename, new_filename, full_filename)
                    if os.path.exists(full_filename):
                        print(f'------跳过-->文件<{full_filename}>已下载...')
                        continue
                    files.append((old_filename, new_filename, full_filename, link3))
                for f1 in files:
                    try:
                        r = requests.get(f1[3], headers=headers)
                        print(r.status_code)
                        with open(f1[2], 'wb') as f:
                            f.write(r.content)
                    except:
                        print(f'>>>except 下载发生错误,跳过下载{f1[3]}')
                        continue

                k += 1

input('请输入......')

【发文章不易，请多多点赞、关注、支持，谢谢！】