df = pd.read_csv(
	path,
	usecols=[0, 5], # 只选择第1列和第6列
	header=None, # None: 不将第一行当做列名，0: 将第一行当做列名， 1: 将第二行当做列名
	names=["target", "text"], # 指定df中的列名
)

df_1 = df[df["target"].isin(["1"])]
print(df["target"].isin(["1"]))
"""
    target
0   True    
1   False     
2   False
"""

print(df_1)
"""
    target
0   1 
"""

from gensim.models.wrappers import FastText

# for *.bin
model = FastText.load_fasttext_format('sample.bin')
# for *.vec
model = FastText.load_word2vec_format('sample.vec')

import pandas as pd
d=[[1,2,3,4],[5,6,7,8]]
index=["one","two"]
df=pd.DataFrame(d, index=index)  
print df.loc["one"]

>>> df.index
RangeIndex(start=0, stop=18, step=1) # 0~17
>>> df.iloc[0] # 获取第一行

df.ix[3] # 读取第三行
df.ix["three"]

# 两个参数，第一个类似切片，指定要获取的行
# 第二个是一个list， 指定要获取的列名
df.ix[:, ["Stations"]]

>>> df.columns
Index(['Station', 'To Tiu Keng Leng', 'To Kwun Tong', 'To Whampoa',
       'Unnamed: 4', 'Unnamed: 5', 'Unnamed: 6'],
      dtype='object')

import numpy as np
l = np.array(df).tolist()

from bs4 import BeautifulSoup as Soup

soup = Soup(open(sample.html), features="lxml")
# soup = Soup('<h1>my title</h1>', features="lxml")
soup.find_all('table') # 通过实例来使用一系列强大功能

soup.table # 等同于 soup.find('table')
soup.find('table') # 第一个出现的table, 类型为<class 'bs4.element.Tag'>
soup.find_all('table') # 所有table

>>> s = Soup('<b>this is sample</b>')
>>> type(s.b)
<class 'bs4.element.Tag'>
>>> s.b.text
'this is sample'

>>> s = Soup('<b>this is sample</b>')
>>> s.b.__repr__()
'<b>this is sample</b>'

import pandas as pd

# 因为会返回包含df的list
df = pd.read_html(html, header=0, encoding="utf8")[0]

r = requests.get(url,**args)#返回一个Response对象，我们可以从这个对象中获取所有我们想要的信息

args = {
	"a": "b",
    ...
}
r = requests.post(url, params=args)#也是返回Response对象

payload = {'key1': 'value1', 'key2': 'value2'}
r = requests.get("http://httpbin.org/get", params=payload)
#相当于目标网址变成了http://httpbin.org/get?key2=value2&key1=value1