百度文库爬虫批量下载

hksnow

前言：

需要对照练习册答案，百度找到了答案，想要下载下来。
代码：

[Python] 纯文本查看 复制代码

import requests
import json
import os
#from concurrent import futures
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0'}
# https://wk.baidu.com/bigque/jsonp/naapi/answer/getwapflowanswerview?na_uncheck=1&pn=1&rn=5&answer_id=fa3ab7c30c22590102029d3f&sign=meow
def download_file(file_url,download_path):
    global file_num
    html = requests.get(file_url,headers = headers)
    file_name = download_path + '\\' + str(file_num) + '.jpg'
    with open(file_name,'wb') as code:
        code.write(html.content)
    file_num = file_num + 1
def start(link):
    global thread
    # 第一次提交为了获取基本信息
    answer_id = link.split('/')[-1]
    url = 'https://wk.baidu.com/bigque/jsonp/naapi/answer/getwapflowanswerview?na_uncheck=1&pn=1&rn=5&answer_id=' + answer_id + '&sign=meow'
    html = requests.get(url,headers = headers)
    json_data = json.loads(html.text)
    img_totals = json_data['data']['answer_info']['pages']
    title = json_data['data']['answer_info']['title']
    page_nums = int(img_totals)//5
    last_page_img_totals = int(img_totals)%5
    # 第二次获取图片数据
    path = os.getcwd() + '\\' + title
    os.makedirs(path)
    for n in range(0,page_nums + 1):
        url = 'https://wk.baidu.com/bigque/jsonp/naapi/answer/getwapflowanswerview?na_uncheck=1&pn=' + str(n) + '&rn=5&answer_id=' + answer_id + '&sign=meow'
        html = requests.get(url,headers = headers)
        json_data = json.loads(html.text)
        answer_urls_list = json_data['data']['answer_urls']
        #print(answer_urls_list)
        if (n == page_nums):
            num_lists = range(0,last_page_img_totals)
            print('最后一页了！')
        else:
            num_lists = range(0,5)
        for x in num_lists:
            img_url = answer_urls_list[x]
            #print(img_url)
            #thread.submit()
            download_file(img_url,path)
if __name__ == "__main__":
    #thread = futures.ThreadPoolExecutor(max_workers = 5)
    file_num = 1
    url = '[/color][/color][/b][/size][size=6][b][color=Red][color=Black]'
    start(url)

仅支持https://wk.baidu.com/bigque/book/xxxxxxxxxx22590102029d3f这样类似的链接

KobeBryantmentu

试试看，源码好评

www1678

有安卓的吗

薄荷叶1996

牛批 大佬

cdwdz

感谢分享  谢谢

淮左名都

mark，学习一下。。。

virgo915

好东西，支持支持

fudashuai

欢迎为大家分享啊！

wty1641

mark..........

s98

厉害了大佬