def d(a, b):
if function == "lcs":
#https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Longest_common_substring#Python_2
m = [[0] * (1 + len(b)) for i in xrange(1 + len(a))]
longest, x_longest = 0, 0
for x in xrange(1, 1 + len(a)):
for y in xrange(1, 1 + len(b)):
if a[x - 1] == b[y - 1]:
m[x][y] = m[x - 1][y - 1] + 1
if m[x][y] > longest:
longest = m[x][y]
x_longest = x
else:
m[x][y] = 0
return len(a[x_longest -
longest:x_longest]) # used to be without len( )
if function == "lenS":
return abs(len(a) - len(b))
if function == "d&l":
import re
lettersa = len(re.findAll("[a-zA-Z]", a))
numbersa = len(re.findAll("[0-9]", a))
lettersb = len(re.findAll("[a-zA-Z]", b))
numbersb = len(re.findAll("[0-9]", b))
return abs(lettersa - lettersb) + abs(numbersa - numbersb)
if function == "edit":
short = min(len(a), len(b))
diff = max(len(a), len(b)) - short
for i in range(short):
if a[i] != b[i]:
diff += 1
return diff
def ScrapePage2(browseTo):
trail = list()
try:
page = urllib.request.urlopen(browseTo)
pageContents = page.read().decode("utf-8")
except:
return
matchObj = re.findall( r'href=[\'"]?([^\'" >]+)', pageContents, 0)
lookObj = re.findAll(lookingFor, pageContents, 0)
if(len(lookObj) > 0)
print("Ding! on " + browseTo)
for i in matchObj:
goodUrl = urljoin(browseTo, i)
if goodUrl not in urls and domain == urlparse(goodUrl).hostname:
trail.append(goodUrl)
urls[goodUrl] = goodUrl#urls.append(goodUrl)
while len(trail) > 0:
e = trail.pop()
print(e)
try:
page = urllib.request.urlopen(e)
pageContents = page.read().decode("utf-8")
except:
continue
matchObj = re.findall( r'href=[\'"]?([^\'" >]+)', pageContents, 0)
for i in matchObj:
goodUrl = urljoin(e, i)
if goodUrl not in urls and domain == urlparse(goodUrl).hostname:
trail.append(goodUrl)
urls[goodUrl] = goodUrl#urls.append(goodUrl)
def getContent(self, page):
pattern = re.compile('<div id="post_content_.*?>(.*?)</div>', re.S)
items = re.findAll(pattern, page)
contents = []
for item in items:
content = "\n" + self.tool.replace(item) + "\n"
contents.append(content.encode('utf-8'))
return contents
def getContent(self, page):
pattern = re.compile('<div id="post_content_.*?>(.*?)</div>',re.S)
items = re.findAll(pattern, page)
contents = []
for item in items:
content = "\n" + self.tool.replace(item) + "\n"
contents.append(content.encode('utf-8'))
return contents
def indentDepth(self, whiteSpace):
#Make sure there is no mixing of tabs and spaces
assert (self.indentToken != "")
if (self.indentToken == "\t"):
assert (" " not in whiteSpace)
else:
assert ("\t" not in whiteSpace)
return len(re.findAll(self.indentToken, whiteSpace))
def indentDepth(self, whiteSpace):
#Make sure there is no mixing of tabs and spaces
assert(self.indentToken != "")
if(self.indentToken == "\t"):
assert(" " not in whiteSpace)
else:
assert("\t" not in whiteSpace)
return len(re.findAll(self.indentToken, whiteSpace))
def getAllBoardsForUser(self , refName):
time.sleep(1)
resp = self.br.open("http://pinterest.com/%s/"%refName)
con = resp.read()
jsonBoard="""var myboards =(.*?[^]]?)]"""
m = re.findAll( re.compile(jsonBoard), con )
print m
content = json.loads(request.read()).get("url")
pinID = string.replace( content , "/pin/" , "" ).replace("/" , "")
return pinID
def processString(self, string, page): """ Given a string chunk form a file runs Reg Exp to detect private info and append a marker to the list 'strings' """ # Regex for proper names regex = '[A-Z][a-zA-Z|.]+' patt = re.compile(regex) matches = re.findAll(patt, string)
def mmInfo(self, path):
content = self.gate.page_source.encode('utf-8')
print("妹子信息页面：")
print(content)
pattern = re.compile('.*?<ul class="mm-p-info-cell clearfix">'+
'.*?<li class=".*?<label>(.*?)</label><span>(.*?)'+
'</span></li>.*?</ul>.*?', re.S)
infoPairs = re.findAll(pattern, content)
fo = open(path+'info.txt', 'w')
for i in range(1,len(infoPairs)-1):
key = infoPairs[i]
value = infoPairs[i+1]
i=i+1
fo.write(key)
fo.write(value + '\n')
fo.close()
def global_reg(pattern,content):
return re.findAll(pattern,content,re.S)
def counter(content):
num_line = re.findAll(PATTERN_LINE, content)
num_block = re.findAll(PATTERN_BLOCK, content)
return len(num_line) + len(num_block)
import urllib,re
from urllib import urlopen
f =urlopen("https://www.justdial.com/Delhi/Baby-Sitters-in-Rohini/nct-10031239")
s = f.read()
print(re.findAll(r"\+\d{2}\s?0?\d{10}",s))
print(re.findAll(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}",s))
from bs4 import BeautifulSoup as parse
from Calendar import Calendar
OUTPUT_FILE_NAME = 'iCal.ics'
GOOGLE_OUTPUT_FILE_NAME = 'iCal_Google.ics'
DOMAIN = 'http://www.techvibes.com'
URL = DOMAIN + '/event/vancouver'
page = openPage(URL)
html = parse(page)
pageList = html.find(class_ = 'pagination')
try:
pageIndex = pageList.find(class_ = 'active').a['title']
numberOfPages = int(findAll('Page 1 of (\d+)', pageIndex)[0])
except AttributeError:
numberOfPages = 1
calendar = Calendar()
for pageNumber in range(1, numberOfPages + 1):
print 'Page', pageNumber
url = URL + '/' + str(pageNumber)
page = openPage(url)
html = parse(page)
content = html.find(id = 'content')
eventListings = content.find_all(class_ = 'event')
import re s = "desc=(ProxyGoodsAnalysisServiceImpl.getGoodsTop)异常" print(s) re.findAll(r"desc=(.+?)", s)
import urllib.parse
import urllib.request
import re
response = urllib.request.urlopen(
"https://in.finance.yahoo.com/quote/AAPL?p=AAPL")
html = response.read()
regex = '<span class="Trsdu(0.3s) Fw(b) Fz(36px) Mb(-4px) D(ib)" data-reactid="247">(.+?)</span>'
pattern = re.compile(regex)
ht = html.decode('utf-8')
price = re.findAll(pattern, ht)
print(price)
def numOfProds( self ):
prods = self.soup.findAll( 'div', 'pag-n-to-n-txt' )
rg = 'of ([0-9]+)'
num = int(re.findAll( rg, prods[0].text )[0])
def global_reg(pattern, content):
return re.findAll(pattern, content, re.S)
import requests
import re
#好饿啊，什么时候开饭
class test:
def __init__(self):
print("初始化jxhczzz")
def getHtmlText(self, url):
try:
html = requests.get(url).text
except:
return None
def resultList(self, html):
for a in html:
print(a)
a = test()
html = a.getHtmlText("http://www.baidu.com")
resultlist = re.findAll(r'\d{3}-\d{7,8}(-\d{\d}?)')
reslt = a.resultList(resultlist)
print("2019-08-17")