前不久 requests 的作者 kennethreitz 出了一个新库 requests-html ,它不仅可以请求网页,还可以解析 HTML 文档,话不多说,咱开始吧。
安装
安装很简单,只要执行:
pip install requests-html
分析页面结构
通过浏览器审查元素可以发现这个电子书网站是用 WordPress 搭建的,首页列表元素很简单,很规整,
所以我们可以查找 .entry-title > a 获取所有图书详情页的链接,接着我们进入详情页,来寻找下载链接,由下图
可以发现 .download-links > a 里的链接就是该书的下载链接,回到列表页可以发现该站一共 700 多页,由此我们便可以循环列表获取所有的下载链接。
构建代码
from requests_html import HTMLSession import requests import time import json import random import sys session = HTMLSession() list_url = 'http://www.allitebooks.com/page/'
#引入浏览器头,防止封ip USER_AGENTS = [ "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1", "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5", "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre", "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11", "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10" ] # 获取当前列表页所有图书链接 def get_list(url): response = session.get(url) all_link = response.html.find('.entry-title a') # 获取页面所有图书详情链接 for link in all_link: getBookUrl(link.attrs['href']) # 获取图书下载链接 def getBookUrl(url): response = session.get(url) l = response.html.find('.download-links a', first=True) if l is not None: # 运行后发现有的个别页面没有下载链接,这里加个判断 link = l.attrs['href']; download(link) #下载图书 def download(url): # 随机浏览器 User-Agent headers={ "User-Agent":random.choice(USER_AGENTS) } # 获取文件名 filename = url.split('/')[-1] # 如果 url 里包含 .pdf if ".pdf" in url: file = 'book/'+filename # 文件路径写死了,运行时当前目录必须有名 book 的文件夹 with open(file, 'wb') as f: print("正在下载 %s" % filename) response = requests.get(url, stream=True, headers=headers) # 获取文件大小 total_length = response.headers.get('content-length') # 如果文件大小不存在,则直接写入返回的文本 if total_length is None: f.write(response.content) else: # 下载进度条 dl = 0 total_length = int(total_length) # 文件大小 for data in response.iter_content(chunk_size=4096): # 每次响应获取 4096 字节 dl += len(data) f.write(data) done = int(50 * dl / total_length) sys.stdout.write(" [%s%s]" % ('=' * done, ' ' * (50-done)) ) # 打印进度条 sys.stdout.flush() print(filename + '下载完成!') if __name__ == '__main__': #从这运行,应知道列表总数,所以偷个懒直接开始循环 for x in range(1,756): print('当前页面: '+ str(x)) get_list(list_url+str(x))