python 小脚本 通过关键词在百度网盘 搜索 高清电影并生成html浏览

比较屌丝，看电影经常用百度云网盘，所以写个脚本方便查看。

1. 保持脚本为 baidu.py，然后 python baidu.py -h 查看帮助。

2. -p：指定第几页； -k：关键词

3. 把符合的电影最后生成Html文件然后浏览（文件位置自己再修改下或者改成动态的吧）。

4. 设置alias：alias baidu="python baidu.py",然后 在命令行中 执行 baidu -p 1 -k 2016

5. 脚本地址：https://github.com/kute/purepythontest/blob/master/test/get_film_from_baidu.py

6. 脚本：

#! /usr/bin/env python# -*- coding: utf-8 -*-# __author__ = 'kute'# __mtime__ = '16/10/22 17:49'"""关键词 过滤  查看 百度网盘的高清电影太懒了我"""import argparseimport requestsfrom bs4 import BeautifulSoupimport dominatefrom dominate.tags import meta, div, table, tr, td, aimport webbrowserclass GetFilm(object):    def __init__(self, page=1, keyword="2016"):        self.page = page or 1        self.keyword = keyword        self.baiduurl = "http://www.baiduyun.me/forum.php?mod=forumdisplay&fid=99&page={}"        self.baidufile = "/Users/kute/Desktop/baidu.html"    def request(self):        print("========1. Curent page is {} and the keyword is {}.========".format(self.page, self.keyword))        res = requests.get(self.baiduurl.format(self.page))        parse = BeautifulSoup(res.text, "html.parser")        tbodylist = parse.select("tbody[id^='normalthread']")        filmlist = []        for tbody in tbodylist:            parse2 = BeautifulSoup(str(tbody.tr.th), "html.parser")            a = parse2.select_one("a[class='s xst']")            if self.keyword:                if a.string.find(self.keyword) != -1:                    filmlist.append((a["href"], a.string))            else:                filmlist.append((a["href"], a.string))        print("========2. Finish scrapy the page and begin generate the html:{}.========".format(self.baidufile))        self.generate_html(filmlist)    def generate_html(self, filmlist):        doc = dominate.document(title='Dominate your HTML')        with doc.head:            meta({"http-equiv": "Content-Type", "content": "text/html; charset=UTF-8"})        with doc:            with div():                with table():                    for url, text in filmlist:                        with tr():                            with td():                                a(text, href=url, target="_blank")        with open(self.baidufile, "w") as f:            f.write(doc.render())        print("========3. All finished, have a look please.========")        webbrowser.open("file://{}".format(self.baidufile), new=0, autoraise=True)def main():    parse = argparse.ArgumentParser(description="Generate films file")    parse.add_argument("-k", "--keyword", help="the film year you want to see, default 2016")    parse.add_argument("-p", "--page", help="next page loop, default 1")    args = parse.parse_args()    g = GetFilm(args.page, args.keyword)    g.request()if __name__ == '__main__':    main()

1. 效果：