2017年6月28日 python爬虫学习

1.写入csv文件
2.lxml的用法
3.自定义字典类的方法
4.bytes解码得到str,str编码得到bytes
5.json

 

1

import csv
import lxml.html
class ScrapcCallback:
    def __init__(self):
        self.witer=csv.writer(open("test.csv","a"))
        self.fields =("name","age","gred")
        self.witer.writerow(self.fields)

2

tree= lxml.html.fromstring(html)
tree.cssselect('#content > p ')

3.

class my_dict:

    def __setitem__(self, folder, result):

        print(bool(folder))
        if not  folder:

            os.mkdir(folder)
        with open("test","wb") as fp:
            fp.write(pickle.dumps(result))
    def __getitem__(self, item):
        if os.path.exists(item):
            with open(item,"rb") as fp:
                return  pickle.load(fp)

#先实例化在使用

4.

s = b"hello world"
print(s, type(s))
# 解码
s_1 = s.decode('utf-8')
print(s_1, type(s_1))
# 编码
s_2 = s_1.encode("utf-8")
print(s_2, type(s_2))

5 

这里我想吐槽下,python竟然不认识这样的.....

string="{'name':'tom'}"

只认这样的.....................oh,god.......

string = '{"name":"tom"}'

哎 ,,,心累啊