数据抽取
丹丹

csv I/O

1
2
3
4
5
6
7
8
import pandas as pd

display(pd.read_csv('2019-06-30_数据抽取_data1.csv'))
display(pd.read_table('2019-06-30_数据抽取_data1.csv', sep=','))
display(pd.read_csv('2019-06-30_数据抽取_data2.csv', header=None))
display(pd.read_csv('2019-06-30_数据抽取_data2.csv', names=['a', 'b', 'c', 'd', 'message']))

# data.to_csv('output.csv')
a b c d message
0 1 2 3 4 hello
1 5 6 7 8 world
2 9 10 11 12 foo
a b c d message
0 1 2 3 4 hello
1 5 6 7 8 world
2 9 10 11 12 foo
0 1 2 3 4
0 1 2 3 4 hello
1 5 6 7 8 world
2 9 10 11 12 foo
a b c d message
0 1 2 3 4 hello
1 5 6 7 8 world
2 9 10 11 12 foo

json

1
2
3
4
5
6
7
8
9
10
11
12
13
14
obj = \
"""
{"姓名": "张三",
"住处": ["天朝", "挖煤国", "万恶的资本主义日不落帝国"],
"宠物": null,
"兄弟": [{"姓名": "李四", "年龄": 25, "宠物": "汪星人"},
{"姓名": "王五", "年龄": 23, "宠物": "喵星人"}]
}
"""

import json
result = json.loads(obj) #<class 'dict'>
result = json.dumps(result, ensure_ascii=False) #<class 'str'>
print(result)
{"姓名": "张三", "住处": ["天朝", "挖煤国", "万恶的资本主义日不落帝国"], "宠物": null, "兄弟": [{"姓名": "李四", "年龄": 25, "宠物": "汪星人"}, {"姓名": "王五", "年龄": 23, "宠物": "喵星人"}]}

XML/HTML

1
2
3
4
5
6
7
8
from lxml.html import parse
from urllib.request import urlopen
import ssl

ssl._create_default_https_context = ssl._create_unverified_context
parsed = parse(urlopen('https://ask.julyedu.com/'))

doc = parsed.getroot()
1
2
3
#拿所有<a>
urls = [lnk.get('href') for lnk in doc.findall('.//a')]
urls
['http://www.julyedu.com/weekend/train9?v=m1',
 'https://www.julyedu.com',
 'https://www.julyedu.com/category/index',
 'https://www.julyedu.com/question',
 'https://oj.julyedu.com/',
 'http://jingsai.julyedu.com/',
 'https://www.julyedu.com/video/index',
 'https://ask.julyedu.com',
 'https://www.julyedu.com/active/qiye',
 None,
 'https://www.julyedu.com/cart',
 'https://passport.julyedu.com/login?redirect=http%3A%2F%2Fask.julyedu.com%2F',
 'https://www.julyedu.com',
 'https://passport.julyedu.com/login?redirect=https%3A%2F%2Fask.julyedu.com%2F',
 'https://www.julyedu.com',
 'https://www.julyedu.com/category/index',
 'https://www.julyedu.com/question/index',
 'https://www.julyedu.com/video/index',
 'https://ask.julyedu.com',
 'https://www.julyedu.com/cart/',
 'https://ask.julyedu.com/explore/',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/explore/category-15',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/explore/category-13',
 'https://ask.julyedu.com/explore/category-18',
 'https://ask.julyedu.com/explore/category-17',
 'https://ask.julyedu.com/explore/category-10',
 'https://ask.julyedu.com/explore/category-16',
 'https://ask.julyedu.com/explore/category-14',
 'https://ask.julyedu.com/explore/category-11',
 'https://ask.julyedu.com/explore/category-4',
 'https://ask.julyedu.com/setting/privacy/#notifications',
 'javascript:;',
 'https://ask.julyedu.com/notifications/',
 '',
 'https://ask.julyedu.com/sort_type-hot__day-7',
 'https://ask.julyedu.com/sort_type-unresponsive',
 '',
 'https://ask.julyedu.com/sort_type-hot__day-7',
 'https://ask.julyedu.com/sort_type-unresponsive',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88655',
 'https://ask.julyedu.com/question/88655#!answer_form',
 'https://ask.julyedu.com/explore/category-14',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88654',
 'https://ask.julyedu.com/question/88654#!answer_form',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88653',
 'https://ask.julyedu.com/question/88653#!answer_form',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88652',
 'https://ask.julyedu.com/question/88652#!answer_form',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88651',
 'https://ask.julyedu.com/question/88651#!answer_form',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88650',
 'https://ask.julyedu.com/question/88650#!answer_form',
 'https://ask.julyedu.com/explore/category-14',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88649',
 'https://ask.julyedu.com/question/88649#!answer_form',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88648',
 'https://ask.julyedu.com/question/88648#!answer_form',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88647',
 'https://ask.julyedu.com/question/88647#!answer_form',
 'https://ask.julyedu.com/explore/category-15',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88646',
 'https://ask.julyedu.com/question/88646#!answer_form',
 'https://ask.julyedu.com/explore/category-13',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1007',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://dwz.cn/O9VznNuY',
 'https://ask.julyedu.com/uploads/article/20190621/489e6c00af84ab51a832781134568131.png',
 'https://ask.julyedu.com/uploads/article/20190621/424770863c018c01543b2630ed9f0153.png',
 'https://ask.julyedu.com/article/1007',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1006',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://dwz.cn/bwUTiuHL',
 'https://ask.julyedu.com/article/1006',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1005',
 'https://ask.julyedu.com/explore/category-15',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://dwz.cn/ZmFmFUmY',
 'https://ask.julyedu.com/article/1005',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1004',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://dwz.cn/kFJZuxek',
 'https://ask.julyedu.com/uploads/article/20190619/eab24a8a5b30672d260dd446d7b21c8b.png',
 'https://ask.julyedu.com/article/1004',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88645',
 'https://ask.julyedu.com/question/88645#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1003',
 'https://ask.julyedu.com/explore/category-13',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://dwz.cn/Ar8fDfbn',
 'https://ask.julyedu.com/uploads/article/20190618/ad20b22eee771ee56e4f674f341ee397.png',
 'https://ask.julyedu.com/article/1003',
 'https://ask.julyedu.com/people/Darlingpan',
 'https://ask.julyedu.com/question/86722',
 'https://ask.julyedu.com/people/%E8%8E%B9%E5%AE%9D%E5%AE%9D',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E8%8E%B9%E5%AE%9D%E5%AE%9D',
 'https://ask.julyedu.com/people/Darlingpan',
 'https://ask.julyedu.com/question/85510',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7545057',
 'https://ask.julyedu.com/explore/category-13',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7545057',
 'https://ask.julyedu.com/people/zdl',
 'https://ask.julyedu.com/question/88644',
 'https://ask.julyedu.com/question/88644#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/zdl',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1002',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://dwz.cn/kRg2NTm0',
 'https://ask.julyedu.com/article/1002',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88643',
 'https://ask.julyedu.com/question/88643#!answer_form',
 'https://ask.julyedu.com/explore/category-13',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/question/88642',
 'https://ask.julyedu.com/question/88642#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/question/88641',
 'https://ask.julyedu.com/question/88641#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/people/%E4%B8%83%E6%9C%88%E5%9C%A8%E7%BA%BF',
 'https://ask.julyedu.com/question/88640',
 'https://ask.julyedu.com/question/88640#!answer_form',
 'https://ask.julyedu.com/explore/category-4',
 'https://ask.julyedu.com/people/%E4%B8%83%E6%9C%88%E5%9C%A8%E7%BA%BF',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88639',
 'https://ask.julyedu.com/question/88639#!answer_form',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88638',
 'https://ask.julyedu.com/question/88638#!answer_form',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1001',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1001',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1000',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/1000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/article/999',
 'https://ask.julyedu.com/explore/category-13',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/uploads/article/20190605/6dcda1628e00ed7dfab23d18431f6c9b.png',
 'https://ask.julyedu.com/article/999',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88634',
 'https://ask.julyedu.com/question/88634#!answer_form',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88633',
 'https://ask.julyedu.com/question/88633#!answer_form',
 'https://ask.julyedu.com/explore/category-18',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88632',
 'https://ask.julyedu.com/question/88632#!answer_form',
 'https://ask.julyedu.com/explore/category-14',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E9%80%86%E8%BD%AC',
 'https://ask.julyedu.com/question/88584',
 'https://ask.julyedu.com/people/%E8%8B%A5%E6%99%B4',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7479632',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/qq%E7%94%A8%E6%88%B7497804',
 'https://ask.julyedu.com/people/',
 'https://ask.julyedu.com/question/86859',
 'https://ask.julyedu.com/people/%E5%BE%AE%E4%BF%A1%E7%94%A8%E6%88%B7488524',
 'https://ask.julyedu.com/people/%E5%BE%AE%E4%BF%A1%E7%94%A8%E6%88%B7480301',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/Michael+Michael',
 'https://ask.julyedu.com/people/%E4%B8%83%E6%9C%88%E5%9C%A8%E7%BA%BF',
 'https://ask.julyedu.com/question/88631',
 'https://ask.julyedu.com/question/88631#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E4%B8%83%E6%9C%88%E5%9C%A8%E7%BA%BF',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/question/88629',
 'https://ask.julyedu.com/question/88629#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/question/88630',
 'https://ask.julyedu.com/question/88630#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/question/88628',
 'https://ask.julyedu.com/question/88628#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88627',
 'https://ask.julyedu.com/question/88627#!answer_form',
 'https://ask.julyedu.com/explore/category-13',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88626',
 'https://ask.julyedu.com/question/88626#!answer_form',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88625',
 'https://ask.julyedu.com/question/88625#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88624',
 'https://ask.julyedu.com/question/88624#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88623',
 'https://ask.julyedu.com/question/88623#!answer_form',
 'https://ask.julyedu.com/explore/category-14',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88622',
 'https://ask.julyedu.com/question/88622#!answer_form',
 'https://ask.julyedu.com/explore/category-1',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88621',
 'https://ask.julyedu.com/question/88621#!answer_form',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/question/88619',
 'https://ask.julyedu.com/question/88619#!answer_form',
 'https://ask.julyedu.com/explore/category-7',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7527000',
 'https://ask.julyedu.com/people/%E5%BC%A0%E7%BF%94',
 'https://ask.julyedu.com/question/88617',
 'https://ask.julyedu.com/question/88617#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E5%BC%A0%E7%BF%94',
 'https://ask.julyedu.com/people/%E5%BC%A0%E7%BF%94',
 'https://ask.julyedu.com/question/88618',
 'https://ask.julyedu.com/question/88618#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E5%BC%A0%E7%BF%94',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/question/88616',
 'https://ask.julyedu.com/question/88616#!answer_form',
 'https://ask.julyedu.com/explore/category-5',
 'https://ask.julyedu.com/people/%E6%89%8B%E6%9C%BA%E7%94%A8%E6%88%B7505476',
 'https://ask.julyedu.com/people/afei3009',
 'https://ask.julyedu.com/question/88615',
 'https://ask.julyedu.com/question/88615#!answer_form',
 'https://ask.julyedu.com/explore/category-13',
 'https://ask.julyedu.com/people/afei3009',
 'javascript:;',
 'https://ask.julyedu.com/sort_type-new__day-0__is_recommend-0__page-2',
 'https://ask.julyedu.com/sort_type-new__day-0__is_recommend-0__page-3',
 'https://ask.julyedu.com/sort_type-new__day-0__is_recommend-0__page-4',
 'https://ask.julyedu.com/sort_type-new__day-0__is_recommend-0__page-2',
 'https://ask.julyedu.com/sort_type-new__day-0__is_recommend-0__page-56',
 'https://ask.julyedu.com/topic/channel-hot',
 'https://ask.julyedu.com/topic/python',
 'https://ask.julyedu.com/topic/python',
 'https://ask.julyedu.com/topic/活动',
 'https://ask.julyedu.com/topic/活动',
 'https://ask.julyedu.com/topic/GAN',
 'https://ask.julyedu.com/topic/GAN',
 'https://ask.julyedu.com/topic/面试',
 'https://ask.julyedu.com/topic/面试',
 'https://ask.julyedu.com/people/',
 'https://ask.julyedu.com/people/xiaoyan2015',
 'https://ask.julyedu.com/people/xiaoyan2015',
 'https://ask.julyedu.com/people/qyzx_zhx',
 'https://ask.julyedu.com/people/qyzx_zhx',
 'https://ask.julyedu.com/people/%E7%A4%BE%E5%8C%BA%E5%B0%8F%E7%AE%A1%E5%AE%B6',
 'https://ask.julyedu.com/people/%E7%A4%BE%E5%8C%BA%E5%B0%8F%E7%AE%A1%E5%AE%B6',
 'https://ask.julyedu.com/people/unasm',
 'https://ask.julyedu.com/people/unasm',
 'https://ask.julyedu.com/people/Alina',
 'https://ask.julyedu.com/people/Alina',
 'http://www.julyedu.com/weekend/train9?v=m1',
 'http://q.url.cn/AB8aue?_type=wpa&qidian=true',
 'http://www.julyedu.com/distribution/index',
 'http://weibo.com/askjulyedu',
 None,
 'https://www.julyedu.com/help/index/about',
 'https://www.julyedu.com/help/index/contact',
 'https://www.julyedu.com/help/index/join',
 'https://ask.julyedu.com/question/55',
 'https://tianchi.aliyun.com',
 'https://cloud.tencent.com/developer/edu',
 'https://www.aidaxue.com/?ch=qyzx',
 'https://www.epubit.com',
 'http://www.miitbeian.gov.cn/',
 'https://www.cnzz.com/stat/website.php?web_id=1259748782',
 'https://www.julyedu.com',
 'https://www.julyedu.com/help/index/about',
 'https://www.julyedu.com/help/index/join',
 'http://weibo.com/askjulyedu',
 'javascript:',
 'https://tianchi.aliyun.com',
 'https://cloud.tencent.com/developer/edu',
 'https://www.aidaxue.com/?ch=qyzx',
 'https://www.epubit.com']

参考:

  1. 廖雪峰Python数据分析