查看某模块路径
Bash
pip show --files selenium
文件编码转换
Bash
convmv -f GBK -t UTF-8 --notest -r ydcz_1/
查找当前目录下,结尾为.php的文件中,包含字符串“zfb_box”的文件
Bash
find ./ -name "*.php" | xargs grep “zfb_box"
百度搜索结果URL提取主域名
Bash
cat xinxi_jieguo|awk -F"," '{print $3}'|egrep -o 'http://[^/]*?/' |egrep -o '([a-z0-9_-]{1,32}\.)+([a-z0-9_-]{1,32})((\.[a-z]{2,4})(.[a-z]{1,2})?)'|egrep -o "\.[^\.]*?\.(com\.cn|com|cn|net|org|cc|hk|tv|info|de|tw|wang|kr)$”
统计每个域名流量分发
Bash
cat xinxi_jieguo|awk -F"," '{print $3}'|egrep '\.1688.com'|egrep -o 'http://[^/]*?/[^/]*?/' | sort|uniq -c|sort -nr
两文件按列合并
Bash
paste -d " " 4+.txt out.txt > hebing.txt
awk计算重复次数
Bash
cat urldata|awk '{a[$1]++}END{for(i in a){print i,a[i]}}'
按列求和
Bash
awk '/aaa/ {sum += $2};END {print sum}’ test
按列求和2
Bash
cat test.txt | awk '{s[$1]+=$2}END{for(i in s){print i,s[i]}}'
按行数将一个文件分割成多个,sitemap使用
Bash
split -8142 file outfile
查找目录下包含某个字符的文件
Bash
find .|xargs grep -ri "IBM"
python下载图片
Python
#! /usr/bin/env python
#coding=utf-8
import url lib,os
filepath=os.getcwd()
if os.path.exists(filepath) is False:
os.mkdir(filepath)
x=1
print u'爬虫准备就绪...'
for line in open('logo_url.txt'):
line = line.strip()
id = line.split(',')[1]
imgurl = line.split(',')[2]
temp= '%s.jpg' % id
print u'正在下载第%s张图片' % x
print imgurl
try:
urllib.urlretrieve(imgurl,temp)
x+=1
except:
continue
print u'图片下载完毕,保存路径为'+filepath
MD5生成
Python
import hashlib
m2 = hashlib.md5()
m2.update(src)
print m2.hexdigest()
读取CSV
Python
# coding: utf-8
import csv
csvfile = file('csv_test.csv', 'rb')
reader = csv.reader(csvfile)
for line in reader:
print line
csvfile.close()
写入CSV
Python
# coding: utf-8
import csv
csvfile = file('csv_test.csv', 'wb')
writer = csv.writer(csvfile)
writer.writerow(['姓名', '年龄', '电话'])
data = [
('小河', '25', '1234567'),
('小芳', '18', '789456')
]
writer.writerows(data)
csvfile.close()
删除中文字符串
Python
#coding: utf-8
import sys
import re
reload(sys)
sys.setdefaultencoding('utf8')
s = """
en: Regular expression is a powerful tool for manipulating text.
zh: 汉语是世界上最优美的语言,正则表达式是一个很有用的工具
jp: 正規表現は非常に役に立つツールテキストを操作することです。
jp-char: あアいイうウえエおオ
kr:정규 표현식은 매우 유용한 도구 텍스트를 조작하는 것입니다.
"""
print "原始utf8字符"
#utf8
print "--------"
print repr(s)
print "--------\n"
#非ansi
re_words=re.compile(r"[\x80-\xff]+")
m = re_words.search(s,0)
print "非ansi字符"
print "--------"
print m
print m.group()
print "--------\n"
#unicode
s = unicode(s)
print "原始unicode字符"
print "--------"
print repr(s)
print "--------\n"
#unicode chinese
re_words = re.compile(u"[\u4e00-\u9fa5]+")
m = re_words.search(s,0)
print "unicode 中文"
print "--------"
print m
print m.group()
res = re.findall(re_words, s) # 查询出所有的匹配字符串
if res:
print "There are %d parts:\n"% len(res)
for r in res:
print "\t",r
print
print "--------\n"
#unicode korean
re_words=re.compile(u"[\uac00-\ud7ff]+")
m = re_words.search(s,0)
print "unicode 韩文"
print "--------"
print m
print m.group()
print "--------\n"
#unicode japanese katakana
re_words=re.compile(u"[\u30a0-\u30ff]+")
m = re_words.search(s,0)
print "unicode 日文 片假名"
print "--------"
print m
print m.group()
print "--------\n"
#unicode japanese hiragana
re_words=re.compile(u"[\u3040-\u309f]+")
m = re_words.search(s,0)
print "unicode 日文 平假名"
print "--------"
print m
print m.group()
print "--------\n"
#unicode cjk Punctuation
re_words=re.compile(u"[\u3000-\u303f\ufb00-\ufffd]+")
m = re_words.search(s,0)
print "unicode 标点符号"
print "--------"
print m
print m.group()
print "--------\n"
通过scrapinghub提取代理ip,抓取海外网页
Python
import requests
from requests.auth import HTTPProxyAuth
url = "http://m.baidu.com/s?word=seo"
headers = {}
proxy_host = "paygo.crawlera.com"
proxy_auth = HTTPProxyAuth("88aa8b802a7f4626b659dae926ee445b", "")
proxies = {"http": "http://proxy.crawlera.com:8010/".format(proxy_host)}
if url.startswith("https:"):
url = "http://" + url[8:]
headers["X-Crawlera-Use-HTTPS"] = "1"
r = requests.get(url, headers=headers, proxies=proxies, auth=proxy_auth)
print r.headers['x-crawlera-slave']
mysql查询数据
Python
def sql_r_num(sql):
cur = con.cursor()
cur.execute(sql)
data = cur.fetchone()
return data[0]
user_nums = sql_r_num("select max(id) from ask_users")
两个时间点之间,随机生成日期
Python
def random_date():
a1=(2018,1,1,0,0,0,0,0,0) #设置开始日期时间元组(1976-01-01 00:00:00)
a2=(2019,4,14,0,0,0,0,0,0) #设置结束日期时间元组(1990-12-31 23:59:59)
start=time.mktime(a1) #生成开始时间戳
end=time.mktime(a2) #生成结束时间戳
#随机生成日期字符串
t=random.randint(start,end) #在开始和结束时间戳中随机取出一个
date_touple=time.localtime(t) #将时间戳生成时间元组
date=time.strftime("%Y-%m-%d %H:%M:%S",date_touple) #将时间元组转成格式化字符串(1976-05-21)
return date
写入mysql
Python
import sys,time,os,smtplib
import MySQLdb as mdb
mysql_time = time.strftime('%Y-%m-%d',time.localtime(time.time()))
con= mdb.connect("23.236.79.228","root","123456”,”seo_data",charset=“utf8”,unix_socket='/tmp/mysql.sock')
cur = con.cursor()
mysql_haosou_uv = '''INSERT INTO haosou_pc_uv VALUES ("%s",%s)''' % (mysql_time,','.join(sql_haosou_uv))
mysql_bd_pc_spider = '''INSERT INTO bd_pc_spider VALUES ("%s",%s)''' % (mysql_time,','.join(sql_bd_pc_spider))
mysql_bd_m_spider = '''INSERT INTO bd_m_spider VALUES ("%s",%s)''' % (mysql_time,','.join(sql_bd_m_spider))
mysql_bd_pc_uv = '''INSERT INTO bd_pc_uv VALUES ("%s",%s)''' % (mysql_time,','.join(sql_bd_pc_uv))
mysql_bd_m_uv = '''INSERT INTO bd_m_uv VALUES ("%s",%s)''' % (mysql_time,','.join(sql_bd_m_uv))
sql_list = [mysql_haosou_uv,mysql_bd_pc_spider,mysql_bd_m_spider,mysql_bd_pc_uv,mysql_bd_m_uv]
for sql in sql_list:
print 'Import:%s' % sql
try:
cur.execute(sql)
con.commit()
print 'done'
except:
con.rollback()
判断字符串是否全部为中文
Python
#coding:utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf8')
'''判断当前字符串是否全部为中文'''
def check_contain_chinese(check_str):
n = 0
m = 0
for ch in check_str.decode('utf-8'):
if u'\u4e00' <= ch <= u'\u9fff':
n += 1
else:
m += 1
if m == 0:
return 1
else:
return 0
文本格式化
Markup
a = re.sub(r'<(?!p|img|/p)[^<>]*?>','',content).strip() #将除p和img之外的标签清空,且去除正文开头结尾的换行,并把单引号换成双引号
b = re.sub(r'<p[^>]*?>','<p>',a) #格式化p标签
newcontent = re.sub(r'alt="[^"]*?"','alt="%s"' % title,b).lower()
提取字符串中文并计算字数
Python
text = re.sub("[\s+\.\!\/_,$%^*(+\"\']+|[+——!,::。?、~@#¥%……&*()“”《》]+".decode("utf8"), "".decode("utf8"),newcontent) #去除中英文标点符号
text2 = re.sub('<[^>]*?>','',text) #去除所有标签
words_number = len(text2)
unicode字符串转义(Python中,如何将反斜杠u类型(\uXXXX)的字符串,转换为对应的unicode的字符)
Python
slashUStr = "\\u0063\\u0072\\u0069\\u0066\\u0061\\u006E\\u0020\\u5728\\u8DEF\\u4E0A"
decodedUniChars = slashUStr.decode("unicode-escape")
print "decodedUniChars=",decodedUniChars
json与dict转化
Python
import simplejson
# JSON转化为字典
json_2_dict = simplejson.loads(user)
print json_2_dict
#字典转化为JSON字符串
dict_2_jsonstr = simplejson.dumps(json_2_dict)
print dict_2_jsonstr
识别客户端类型
Python
def getUA(ua):
reg_b = re.compile(r"(android|bb\\d+|meego).+mobile|avantgo|bada\\/|blackberry|blazer|compal|elaine|fennec|hiptop|iemobile|ip(hone|od)|iris|kindle|lge |maemo|midp|mmp|mobile.+firefox|netfront|opera m(ob|in)i|palm( os)?|phone|p(ixi|re)\\/|plucker|pocket|psp|series(4|6)0|symbian|treo|up\\.(browser|link)|vodafone|wap|windows ce|xda|xiino", re.I|re.M)
reg_v = re.compile(r"1207|6310|6590|3gso|4thp|50[1-6]i|770s|802s|a wa|abac|ac(er|oo|s\\-)|ai(ko|rn)|al(av|ca|co)|amoi|an(ex|ny|yw)|aptu|ar(ch|go)|as(te|us)|attw|au(di|\\-m|r |s )|avan|be(ck|ll|nq)|bi(lb|rd)|bl(ac|az)|br(e|v)w|bumb|bw\\-(n|u)|c55\\/|capi|ccwa|cdm\\-|cell|chtm|cldc|cmd\\-|co(mp|nd)|craw|da(it|ll|ng)|dbte|dc\\-s|devi|dica|dmob|do(c|p)o|ds(12|\\-d)|el(49|ai)|em(l2|ul)|er(ic|k0)|esl8|ez([4-7]0|os|wa|ze)|fetc|fly(\\-|_)|g1 u|g560|gene|gf\\-5|g\\-mo|go(\\.w|od)|gr(ad|un)|haie|hcit|hd\\-(m|p|t)|hei\\-|hi(pt|ta)|hp( i|ip)|hs\\-c|ht(c(\\-| |_|a|g|p|s|t)|tp)|hu(aw|tc)|i\\-(20|go|ma)|i230|iac( |\\-|\\/)|ibro|idea|ig01|ikom|im1k|inno|ipaq|iris|ja(t|v)a|jbro|jemu|jigs|kddi|keji|kgt( |\\/)|klon|kpt |kwc\\-|kyo(c|k)|le(no|xi)|lg( g|\\/(k|l|u)|50|54|\\-[a-w])|libw|lynx|m1\\-w|m3ga|m50\\/|ma(te|ui|xo)|mc(01|21|ca)|m\\-cr|me(rc|ri)|mi(o8|oa|ts)|mmef|mo(01|02|bi|de|do|t(\\-| |o|v)|zz)|mt(50|p1|v )|mwbp|mywa|n10[0-2]|n20[2-3]|n30(0|2)|n50(0|2|5)|n7(0(0|1)|10)|ne((c|m)\\-|on|tf|wf|wg|wt)|nok(6|i)|nzph|o2im|op(ti|wv)|oran|owg1|p800|pan(a|d|t)|pdxg|pg(13|\\-([1-8]|c))|phil|pire|pl(ay|uc)|pn\\-2|po(ck|rt|se)|prox|psio|pt\\-g|qa\\-a|qc(07|12|21|32|60|\\-[2-7]|i\\-)|qtek|r380|r600|raks|rim9|ro(ve|zo)|s55\\/|sa(ge|ma|mm|ms|ny|va)|sc(01|h\\-|oo|p\\-)|sdk\\/|se(c(\\-|0|1)|47|mc|nd|ri)|sgh\\-|shar|sie(\\-|m)|sk\\-0|sl(45|id)|sm(al|ar|b3|it|t5)|so(ft|ny)|sp(01|h\\-|v\\-|v )|sy(01|mb)|t2(18|50)|t6(00|10|18)|ta(gt|lk)|tcl\\-|tdg\\-|tel(i|m)|tim\\-|t\\-mo|to(pl|sh)|ts(70|m\\-|m3|m5)|tx\\-9|up(\\.b|g1|si)|utst|v400|v750|veri|vi(rg|te)|vk(40|5[0-3]|\\-v)|vm40|voda|vulc|vx(52|53|60|61|70|80|81|83|85|98)|w3c(\\-| )|webc|whit|wi(g |nc|nw)|wmlb|wonu|x700|yas\\-|your|zeto|zte\\-", re.I|re.M)
b = reg_b.search(ua)
v = reg_v.search(ua[0:4])
if b or v:
return 'wap'
else:
return 'pc'
日期遍历
Python
import datatime,time
def date_range(start, end, only_monday=False, input_format='%y%m%d', output_format='%y%m%d'):
'''如print date_range(140130, 140202)
输出['140130', '140131', '140201', '140202']
'''
start = str(start)
end = str(end)
start = datetime.datetime.strptime(start, input_format)
end = datetime.datetime.strptime(end, input_format)
one_day = datetime.timedelta(days=1)
range_ = []
d = start - one_day
while 1:
d = d + one_day
if d > end:
break
if only_monday and d.strftime('%w')!='1':
continue
range_.append(datetime.datetime.strftime(d, output_format))
return range_
查看某模块路径
Bash
pip show --files selenium
文件编码转换
Bash
convmv -f GBK -t UTF-8 --notest -r ydcz_1/
查找当前目录下,结尾为.php的文件中,包含字符串“zfb_box”的文件
Bash
find ./ -name "*.php" | xargs grep “zfb_box"
百度搜索结果URL提取主域名
Bash
cat xinxi_jieguo|awk -F"," '{print $3}'|egrep -o 'http://[^/]*?/' |egrep -o '([a-z0-9_-]{1,32}\.)+([a-z0-9_-]{1,32})((\.[a-z]{2,4})(.[a-z]{1,2})?)'|egrep -o "\.[^\.]*?\.(com\.cn|com|cn|net|org|cc|hk|tv|info|de|tw|wang|kr)$”
统计每个域名流量分发
Bash
cat xinxi_jieguo|awk -F"," '{print $3}'|egrep '\.1688.com'|egrep -o 'http://[^/]*?/[^/]*?/' | sort|uniq -c|sort -nr
两文件按列合并
Bash
paste -d " " 4+.txt out.txt > hebing.txt
awk计算重复次数
Bash
cat urldata|awk '{a[$1]++}END{for(i in a){print i,a[i]}}'
按列求和
Bash
awk '/aaa/ {sum += $2};END {print sum}’ test
按列求和2
Bash
cat test.txt | awk '{s[$1]+=$2}END{for(i in s){print i,s[i]}}'
按行数将一个文件分割成多个,sitemap使用
Bash
split -8142 file outfile
查找目录下包含某个字符的文件
Bash
find .|xargs grep -ri "IBM"
python下载图片
Python
#! /usr/bin/env python
#coding=utf-8
import url lib,os
filepath=os.getcwd()
if os.path.exists(filepath) is False:
os.mkdir(filepath)
x=1
print u'爬虫准备就绪...'
for line in open('logo_url.txt'):
line = line.strip()
id = line.split(',')[1]
imgurl = line.split(',')[2]
temp= '%s.jpg' % id
print u'正在下载第%s张图片' % x
print imgurl
try:
urllib.urlretrieve(imgurl,temp)
x+=1
except:
continue
print u'图片下载完毕,保存路径为'+filepath
MD5生成
Python
import hashlib
m2 = hashlib.md5()
m2.update(src)
print m2.hexdigest()
读取CSV
Python
# coding: utf-8
import csv
csvfile = file('csv_test.csv', 'rb')
reader = csv.reader(csvfile)
for line in reader:
print line
csvfile.close()
写入CSV
Python
# coding: utf-8
import csv
csvfile = file('csv_test.csv', 'wb')
writer = csv.writer(csvfile)
writer.writerow(['姓名', '年龄', '电话'])
data = [
('小河', '25', '1234567'),
('小芳', '18', '789456')
]
writer.writerows(data)
csvfile.close()
删除中文字符串
Python
#coding: utf-8
import sys
import re
reload(sys)
sys.setdefaultencoding('utf8')
s = """
en: Regular expression is a powerful tool for manipulating text.
zh: 汉语是世界上最优美的语言,正则表达式是一个很有用的工具
jp: 正規表現は非常に役に立つツールテキストを操作することです。
jp-char: あアいイうウえエおオ
kr:정규 표현식은 매우 유용한 도구 텍스트를 조작하는 것입니다.
"""
print "原始utf8字符"
#utf8
print "--------"
print repr(s)
print "--------\n"
#非ansi
re_words=re.compile(r"[\x80-\xff]+")
m = re_words.search(s,0)
print "非ansi字符"
print "--------"
print m
print m.group()
print "--------\n"
#unicode
s = unicode(s)
print "原始unicode字符"
print "--------"
print repr(s)
print "--------\n"
#unicode chinese
re_words = re.compile(u"[\u4e00-\u9fa5]+")
m = re_words.search(s,0)
print "unicode 中文"
print "--------"
print m
print m.group()
res = re.findall(re_words, s) # 查询出所有的匹配字符串
if res:
print "There are %d parts:\n"% len(res)
for r in res:
print "\t",r
print
print "--------\n"
#unicode korean
re_words=re.compile(u"[\uac00-\ud7ff]+")
m = re_words.search(s,0)
print "unicode 韩文"
print "--------"
print m
print m.group()
print "--------\n"
#unicode japanese katakana
re_words=re.compile(u"[\u30a0-\u30ff]+")
m = re_words.search(s,0)
print "unicode 日文 片假名"
print "--------"
print m
print m.group()
print "--------\n"
#unicode japanese hiragana
re_words=re.compile(u"[\u3040-\u309f]+")
m = re_words.search(s,0)
print "unicode 日文 平假名"
print "--------"
print m
print m.group()
print "--------\n"
#unicode cjk Punctuation
re_words=re.compile(u"[\u3000-\u303f\ufb00-\ufffd]+")
m = re_words.search(s,0)
print "unicode 标点符号"
print "--------"
print m
print m.group()
print "--------\n"
通过scrapinghub提取代理ip,抓取海外网页
Python
import requests
from requests.auth import HTTPProxyAuth
url = "http://m.baidu.com/s?word=seo"
headers = {}
proxy_host = "paygo.crawlera.com"
proxy_auth = HTTPProxyAuth("88aa8b802a7f4626b659dae926ee445b", "")
proxies = {"http": "http://proxy.crawlera.com:8010/".format(proxy_host)}
if url.startswith("https:"):
url = "http://" + url[8:]
headers["X-Crawlera-Use-HTTPS"] = "1"
r = requests.get(url, headers=headers, proxies=proxies, auth=proxy_auth)
print r.headers['x-crawlera-slave']
mysql查询数据
Python
def sql_r_num(sql):
cur = con.cursor()
cur.execute(sql)
data = cur.fetchone()
return data[0]
user_nums = sql_r_num("select max(id) from ask_users")
两个时间点之间,随机生成日期
Python
def random_date():
a1=(2018,1,1,0,0,0,0,0,0) #设置开始日期时间元组(1976-01-01 00:00:00)
a2=(2019,4,14,0,0,0,0,0,0) #设置结束日期时间元组(1990-12-31 23:59:59)
start=time.mktime(a1) #生成开始时间戳
end=time.mktime(a2) #生成结束时间戳
#随机生成日期字符串
t=random.randint(start,end) #在开始和结束时间戳中随机取出一个
date_touple=time.localtime(t) #将时间戳生成时间元组
date=time.strftime("%Y-%m-%d %H:%M:%S",date_touple) #将时间元组转成格式化字符串(1976-05-21)
return date
写入mysql
Python
import sys,time,os,smtplib
import MySQLdb as mdb
mysql_time = time.strftime('%Y-%m-%d',time.localtime(time.time()))
con= mdb.connect("23.236.79.228","root","123456”,”seo_data",charset=“utf8”,unix_socket='/tmp/mysql.sock')
cur = con.cursor()
mysql_haosou_uv = '''INSERT INTO haosou_pc_uv VALUES ("%s",%s)''' % (mysql_time,','.join(sql_haosou_uv))
mysql_bd_pc_spider = '''INSERT INTO bd_pc_spider VALUES ("%s",%s)''' % (mysql_time,','.join(sql_bd_pc_spider))
mysql_bd_m_spider = '''INSERT INTO bd_m_spider VALUES ("%s",%s)''' % (mysql_time,','.join(sql_bd_m_spider))
mysql_bd_pc_uv = '''INSERT INTO bd_pc_uv VALUES ("%s",%s)''' % (mysql_time,','.join(sql_bd_pc_uv))
mysql_bd_m_uv = '''INSERT INTO bd_m_uv VALUES ("%s",%s)''' % (mysql_time,','.join(sql_bd_m_uv))
sql_list = [mysql_haosou_uv,mysql_bd_pc_spider,mysql_bd_m_spider,mysql_bd_pc_uv,mysql_bd_m_uv]
for sql in sql_list:
print 'Import:%s' % sql
try:
cur.execute(sql)
con.commit()
print 'done'
except:
con.rollback()
判断字符串是否全部为中文
Python
#coding:utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf8')
'''判断当前字符串是否全部为中文'''
def check_contain_chinese(check_str):
n = 0
m = 0
for ch in check_str.decode('utf-8'):
if u'\u4e00' <= ch <= u'\u9fff':
n += 1
else:
m += 1
if m == 0:
return 1
else:
return 0
文本格式化
Markup
a = re.sub(r'<(?!p|img|/p)[^<>]*?>','',content).strip() #将除p和img之外的标签清空,且去除正文开头结尾的换行,并把单引号换成双引号
b = re.sub(r'<p[^>]*?>','<p>',a) #格式化p标签
newcontent = re.sub(r'alt="[^"]*?"','alt="%s"' % title,b).lower()
提取字符串中文并计算字数
Python
text = re.sub("[\s+\.\!\/_,$%^*(+\"\']+|[+——!,::。?、~@#¥%……&*()“”《》]+".decode("utf8"), "".decode("utf8"),newcontent) #去除中英文标点符号
text2 = re.sub('<[^>]*?>','',text) #去除所有标签
words_number = len(text2)
unicode字符串转义(Python中,如何将反斜杠u类型(\uXXXX)的字符串,转换为对应的unicode的字符)
Python
slashUStr = "\\u0063\\u0072\\u0069\\u0066\\u0061\\u006E\\u0020\\u5728\\u8DEF\\u4E0A"
decodedUniChars = slashUStr.decode("unicode-escape")
print "decodedUniChars=",decodedUniChars
json与dict转化
Python
import simplejson
# JSON转化为字典
json_2_dict = simplejson.loads(user)
print json_2_dict
#字典转化为JSON字符串
dict_2_jsonstr = simplejson.dumps(json_2_dict)
print dict_2_jsonstr
识别客户端类型
Python
def getUA(ua):
reg_b = re.compile(r"(android|bb\\d+|meego).+mobile|avantgo|bada\\/|blackberry|blazer|compal|elaine|fennec|hiptop|iemobile|ip(hone|od)|iris|kindle|lge |maemo|midp|mmp|mobile.+firefox|netfront|opera m(ob|in)i|palm( os)?|phone|p(ixi|re)\\/|plucker|pocket|psp|series(4|6)0|symbian|treo|up\\.(browser|link)|vodafone|wap|windows ce|xda|xiino", re.I|re.M)
reg_v = re.compile(r"1207|6310|6590|3gso|4thp|50[1-6]i|770s|802s|a wa|abac|ac(er|oo|s\\-)|ai(ko|rn)|al(av|ca|co)|amoi|an(ex|ny|yw)|aptu|ar(ch|go)|as(te|us)|attw|au(di|\\-m|r |s )|avan|be(ck|ll|nq)|bi(lb|rd)|bl(ac|az)|br(e|v)w|bumb|bw\\-(n|u)|c55\\/|capi|ccwa|cdm\\-|cell|chtm|cldc|cmd\\-|co(mp|nd)|craw|da(it|ll|ng)|dbte|dc\\-s|devi|dica|dmob|do(c|p)o|ds(12|\\-d)|el(49|ai)|em(l2|ul)|er(ic|k0)|esl8|ez([4-7]0|os|wa|ze)|fetc|fly(\\-|_)|g1 u|g560|gene|gf\\-5|g\\-mo|go(\\.w|od)|gr(ad|un)|haie|hcit|hd\\-(m|p|t)|hei\\-|hi(pt|ta)|hp( i|ip)|hs\\-c|ht(c(\\-| |_|a|g|p|s|t)|tp)|hu(aw|tc)|i\\-(20|go|ma)|i230|iac( |\\-|\\/)|ibro|idea|ig01|ikom|im1k|inno|ipaq|iris|ja(t|v)a|jbro|jemu|jigs|kddi|keji|kgt( |\\/)|klon|kpt |kwc\\-|kyo(c|k)|le(no|xi)|lg( g|\\/(k|l|u)|50|54|\\-[a-w])|libw|lynx|m1\\-w|m3ga|m50\\/|ma(te|ui|xo)|mc(01|21|ca)|m\\-cr|me(rc|ri)|mi(o8|oa|ts)|mmef|mo(01|02|bi|de|do|t(\\-| |o|v)|zz)|mt(50|p1|v )|mwbp|mywa|n10[0-2]|n20[2-3]|n30(0|2)|n50(0|2|5)|n7(0(0|1)|10)|ne((c|m)\\-|on|tf|wf|wg|wt)|nok(6|i)|nzph|o2im|op(ti|wv)|oran|owg1|p800|pan(a|d|t)|pdxg|pg(13|\\-([1-8]|c))|phil|pire|pl(ay|uc)|pn\\-2|po(ck|rt|se)|prox|psio|pt\\-g|qa\\-a|qc(07|12|21|32|60|\\-[2-7]|i\\-)|qtek|r380|r600|raks|rim9|ro(ve|zo)|s55\\/|sa(ge|ma|mm|ms|ny|va)|sc(01|h\\-|oo|p\\-)|sdk\\/|se(c(\\-|0|1)|47|mc|nd|ri)|sgh\\-|shar|sie(\\-|m)|sk\\-0|sl(45|id)|sm(al|ar|b3|it|t5)|so(ft|ny)|sp(01|h\\-|v\\-|v )|sy(01|mb)|t2(18|50)|t6(00|10|18)|ta(gt|lk)|tcl\\-|tdg\\-|tel(i|m)|tim\\-|t\\-mo|to(pl|sh)|ts(70|m\\-|m3|m5)|tx\\-9|up(\\.b|g1|si)|utst|v400|v750|veri|vi(rg|te)|vk(40|5[0-3]|\\-v)|vm40|voda|vulc|vx(52|53|60|61|70|80|81|83|85|98)|w3c(\\-| )|webc|whit|wi(g |nc|nw)|wmlb|wonu|x700|yas\\-|your|zeto|zte\\-", re.I|re.M)
b = reg_b.search(ua)
v = reg_v.search(ua[0:4])
if b or v:
return 'wap'
else:
return 'pc'
日期遍历
Python
import datatime,time
def date_range(start, end, only_monday=False, input_format='%y%m%d', output_format='%y%m%d'):
'''如print date_range(140130, 140202)
输出['140130', '140131', '140201', '140202']
'''
start = str(start)
end = str(end)
start = datetime.datetime.strptime(start, input_format)
end = datetime.datetime.strptime(end, input_format)
one_day = datetime.timedelta(days=1)
range_ = []
d = start - one_day
while 1:
d = d + one_day
if d > end:
break
if only_monday and d.strftime('%w')!='1':
continue
range_.append(datetime.datetime.strftime(d, output_format))
return range_