正则表达式，re模块
一，正则表达式
正则表达式是对字符串操作的一种逻辑公式，我们一般使用正则表达式对字符串进行匹配和过滤，使用正则的优缺点，我们可以去http://tool.chinaz.com/regex/进行测试。
优点：灵活，功能性强，逻辑性强
缺点：上手难，一旦上手，使用起来很方便
正则表达式由普通字符和元字符组成，普通字符包含大小写字母，数字，在匹配普通字符的时候我们直接写就好，比如‘abc’匹配的就是‘abc’。元字符才是正则表达式的灵魂。
1，字符组：字符组很简单，用[]括起来，在[]中出现的内容会被匹配，例如[abc]匹配a或b或c，如果字符组中的内容过多还可以使用-，例如[a-z]匹配a到z之间的所有字母，[0-9]匹配所有阿拉伯数字
2，简单元字符
3，量词
4，惰性匹配和贪婪匹配
5，分组
6，转义
二，re模块
三，实例一，用re和urllib爬电影下载地址，我爬的是电影天堂小片网的电影（中间一大段if，elif只是排除编码有问题电影）
from urllib.request import urlopen
import re
for i in range(1,302):
if i ==1:
url='https://www.dy2018.com/html/gndy/dyzz/index.html'
else:
url='https://www.dy2018.com/html/gndy/dyzz/index_%s.html'%i
print(url)
f1 = open('move.txt', mode='a', encoding='utf-8')
f1.write(url + '\n')
f1.close()
content=urlopen(url).read().decode('gbk')
if i==51:
obj = re.compile(r'<td height="20" style="padding-left:3px"> </td>.*?<td height="26">.*?a href="/(?P<adress>.*?)".*?">(?P<name>.*?)</a>', re.S)
else:
obj = re.compile(r'<td height="26">.*?a href="/(?P<adress>.*?)".*?">(?P<name>.*?)</', re.S)
ss=obj.finditer(content)
for el in ss:
if el.group('adress')=='i/91900.html' or el.group('adress')=='html/gndy/dyzz/20130913/91826.html' :
continue
elif el.group('adress')=='html/gndy/dyzz/20130131/41375.html'or el.group('adress')=='html/gndy/dyzz/20130903/91759.html':
continue
elif el.group('adress')=='html/gndy/dyzz/20130908/91797.html'or el.group('adress')=='html/gndy/dyzz/20120623/38354.html':
continue
elif el.group('adress')=='html/gndy/dyzz/20110219/30940.html'or el.group('adress')=='html/gndy/dyzz/20110112/30354.html':
continue
elif el.group('adress')=='html/gndy/dyzz/20110109/30300.html'or el.group('adress')=='html/gndy/dyzz/20110107/30267.html':
continue
elif el.group('adress')=='html/gndy/dyzz/20101231/30152.html'or el.group('adress')=='html/gndy/dyzz/20101231/30150.html':
continue
elif el.group('adress')=='html/gndy/dyzz/20101221/29988.html'or el.group('adress')=='html/gndy/dyzz/20101215/29886.html':
continue
elif el.group('adress')=='html/gndy/dyzz/20101209/29780.html'or el.group('adress')=='html/gndy/dyzz/20101208/29768.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20101101/29127.html'or el.group('adress') == 'html/gndy/dyzz/20101027/29031.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20101019/28883.html'or el.group('adress') == 'html/gndy/dyzz/20100919/28321.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20100909/28122.html'or el.group('adress') == 'html/gndy/dyzz/20100828/27899.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20100820/27742.html'or el.group('adress') == 'html/gndy/dyzz/20100726/27308.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20100620/26683.html'or el.group('adress') == 'html/gndy/dyzz/20100613/26564.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20100428/25809.html'or el.group('adress') == 'html/gndy/dyzz/20100116/24050.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20100110/23933.html'or el.group('adress') == 'html/gndy/dyzz/20100103/23790.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20091104/22691.html'or el.group('adress') == 'html/gndy/dyzz/20090423/18292.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20090308/17370.html'or el.group('adress') == 'html/gndy/dyzz/20090303/17285.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20090308/17377.html'or el.group('adress') == 'html/gndy/dyzz/20090113/16496.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20081221/16079.html'or el.group('adress') == 'html/gndy/dyzz/20081215/15964.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20081008/14637.html'or el.group('adress') == 'html/gndy/dyzz/20080916/14200.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20080905/13985.html'or el.group('adress') == 'html/gndy/dyzz/20080119/9339.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20071213/8253.html'or el.group('adress') == 'html/gndy/dyzz/20071125/7635.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20071025/6879.html'or el.group('adress') == 'html/gndy/dyzz/20070902/5424.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20070824/5143.html'or el.group('adress') == 'html/gndy/dyzz/20070823/5109.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20070823/5088.html'or el.group('adress') == 'html/gndy/dyzz/20070806/4621.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20070805/4617.html'or el.group('adress') == 'html/gndy/dyzz/20070805/4611.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20070727/4333.html'or el.group('adress') == 'html/gndy/dyzz/20070726/4301.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20070716/4023.html'or el.group('adress') == 'html/gndy/dyzz/20070712/3862.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20070617/3072.html'or el.group('adress') == 'html/gndy/dyzz/20070615/3019.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20070527/2418.html'or el.group('adress') == 'html/gndy/dyzz/20070425/1672.html':
continue
elif el.group('adress') == 'html/gndy/dyzz/20070416/1478.html'or el.group('adress') == 'html/gndy/dyzz/20070412/1399.html':
continue
d1={}
d1['name']=el.group('name')
url1='https://www.dy2018.com/'+el.group('adress')
content1 = urlopen(url1).read().decode('gbk')
obj1=re.compile(r'下载地址.*?<a href="(?P<adress1>.*?)">',re.S)
ss1=obj1.search(content1)
d1['adress']=ss1.group('adress1')
f1=open('move.txt',mode='a',encoding='utf-8')
f1.write(str(d1)+'\n')
f1.close()
四，用re和urllib爬维密图片
import re
from urllib.request import urlopen,urlretrieve
for n in range(1,5):
if n ==1:
url2 = 'https://stock.tuchong.com/topic?topicId=49282'
else:
url2='https://stock.tuchong.com/topic?topicId=49282&page=%s&count=100'%n
content=urlopen(url2).read().decode('utf-8')
obj=re.compile(r'"imageId":"(?P<bianhao>.*?)"',re.S)
ss=obj.finditer(content)
i=(n-1)*100+1
for el in ss:
num=el.group('bianhao')
if num=='525558981780570122'or num=='525569719200382978':
continue
elif num=='525589673617915918'or num=='525563551629443081':
continue
elif num == '525571411419332618'or num == '525585163906711562':
continue
elif num == '525554334627135503'or num == '525554274497593347':
continue
elif num == '525555872228048910'or num == '525555889405689865':
continue
elif num == '525566472207728651'or num == '525569650482741255':
continue
elif num == '525571420010053640'or num == '525571196669132802':
continue
elif num == '525571239618281484'or num == '525575964084666381':
continue
elif num == '525577347064528914'or num == '525580594059804675':
continue
elif num == '525592946387451916'or num == '525602292234190873':
continue
elif num == '525551036092645412'or num == '525552685360087057':
continue
elif num == '525554300266217477'or num == '525555657477062662':
continue
elif num == '525557349694570506'or num == '525557418413522955':
continue
elif num == '525575757924401164'or num == '525585146722910211':
continue
elif num == '525591194036862980'or num == '525594604244828160':
continue
elif num == '525619248767172615'or num == '525546397526392859':
continue
elif num == '525547952305733639'or num == '525549618751864836':
continue
elif num == '525552539333034011'or num == '525560631049584650':
continue
elif num == '525561910952460294'or num == '525577252573020167':
continue
elif num == '525577390015905802'or num == '525578919019806730':
continue
elif num == '525589845421064206'or num == '525600746043736066':
continue
elif num == '525600746046750729'or num == '525600539888320533':
continue
elif num == '525636059267465227'or num == '525551070454611970':
continue
elif num == '525551173533827166'or num == '525552693952643113':
continue
elif num == '525557461366341633'or num == '525557169308041219':
continue
elif num == '525558818575613969'or num == '525559024730243078':
continue
elif num == '525560596692074509'or num == '525563345468391437':
continue
elif num == '525575809462435842'or num == '525578901843083269':
continue
elif num == '525580405077442575'or num == '525582148835344441':
continue
elif num == '525585146721337349'or num == '525549532855926790':
continue
elif num == '525552711133822979'or num == '525560338990235661':
continue
elif num == '525565097818193935'or num == '525566489386811399':
continue
elif num == '525569684840644622'or num == '525571239620640780':
continue
elif num == '525571316927692806'or num == '525572725675917316':
continue
elif num == '525573017733693460'or num == '525574254687682562':
continue
elif num == '525574538153689102'or num == '525575869593550849':
continue
elif num == '525594295007182858'or num == '525596004400234497':
continue
elif num == '525608305186177028'or num == '525650120992096265':
continue
elif num == '525564900245504013':
continue
s='http://p3.pstatp.com/weili/ms/%s.webp'%num
print(s)
ss=urlretrieve(s,'维密\%s.jpg'%i)
i += 1
