So, i have a function, which aim is to color words if they are surrounded by commas.
def __init__(...something):
...something
self.user_input = QtGui.QTextEdit(self)
self.user_input.textChanged.connect(self.check_text)
...something
def check_text(self):
text = self.user_input.toPlainText().strip()
comma = ","
if comma in text:
elements_quantity = text.count(comma)
sites = text.split(comma)
sites_quantity = len(sites)
done_sites = []
if sites_quantity > elements_quantity:
done_sites = sites[:elements_quantity]
else:
done_sites = sites
else:
done_sites = [""]
for site in done_sites:
new_site = "<strong>{site}</strong>"
text = text.replace(site, new_site.format(site=site))
self.user_input.setHtml(text)
self.user_input.moveCursor(QtGui.QTextCursor.End)
And, when I start writing, I have RecursionError: maximum recursion depth exceeded while calling a Python object each time I write a symbol.
What I should to do to improve it?
Just block signals when you try to change the text
self.blockSignal(True)
self.user_input.setHtml(text)
self.user_input.moveCursor(QtGui.QTextCursor.End)
self.blockSignal(False)
Related
I am trying to scrape data from a word document available at:-
https://dl.dropbox.com/s/pj82qrctzkw9137/HE%20Distributors.docx
I need to scrape the Name, Address, City, State, and Email ID. I am able to scrape the E-mail using the below code.
import docx
content = docx.Document('HE Distributors.docx')
location = []
for i in range(len(content.paragraphs)):
stat = content.paragraphs[i].text
if 'Email' in stat:
location.append(i)
for i in location:
print(content.paragraphs[i].text)
I tried to use the steps mentioned:
How to read data from .docx file in python pandas?
I need to convert this into a data frame with all the columns mentioned above.
Still facing issues with the same.
There are some inconsistencies in the document - phone numbers starting with Tel: sometimes, and Tel.: other times, and even Te: once, and I noticed one of the emails is just in the last line for that distributor without the Email: prefix, and the State isn't always in the last line.... Still, for the most part, most of the data can be extracted with regex and/or splits.
The distributors are separated by empty lines, and the names are in a different color - so I defined this function to get the font color of any paragraph from its xml:
# from bs4 import BeautifulSoup
def getParaColor(para):
try:
return BeautifulSoup(
para.paragraph_format.element.xml, 'xml'
).find('color').get('w:val')
except:
return ''
The try...except hasn't been necessary yet, but just in case...
(The xml is actually also helpful for double-checking that .text hasn't missed anything - in my case, I noticed that the email for Shri Adhya Educational Books wasn't getting extracted.)
Then, you can process the paragraphs from docx.Document with a function like:
# import re
def splitParas(paras):
ptc = [(
p.text, getParaColor(p), p.paragraph_format.element.xml
) for p in paras]
curSectn = 'UNKNOWN'
splitBlox = [{}]
for pt, pc, px in ptc:
# double-check for missing text
xmlText = BeautifulSoup(px, 'xml').text
xmlText = ' '.join([s for s in xmlText.split() if s != ''])
if len(xmlText) > len(pt): pt = xmlText
# initiate
if not pt:
if splitBlox[-1] != {}:
splitBlox.append({})
continue
if pc == '20752E':
curSectn = pt.strip()
continue
if splitBlox[-1] == {}:
splitBlox[-1]['section'] = curSectn
splitBlox[-1]['raw'] = []
splitBlox[-1]['Name'] = []
splitBlox[-1]['address_raw'] = []
# collect
splitBlox[-1]['raw'].append(pt)
if pc == 'D12229':
splitBlox[-1]['Name'].append(pt)
elif re.search("^Te.*:.*", pt):
splitBlox[-1]['tel_raw'] = re.sub("^Te.*:", '', pt).strip()
elif re.search("^Mob.*:.*", pt):
splitBlox[-1]['mobile_raw'] = re.sub("^Mob.*:", '', pt).strip()
elif pt.startswith('Email:') or re.search(".*[#].*[.].*", pt):
splitBlox[-1]['Email'] = pt.replace('Email:', '').strip()
else:
splitBlox[-1]['address_raw'].append(pt)
# some cleanup
if splitBlox[-1] == {}: splitBlox = splitBlox[:-1]
for i in range(len(splitBlox)):
addrsParas = splitBlox[i]['address_raw'] # for later
# join lists into strings
splitBlox[i]['Name'] = ' '.join(splitBlox[i]['Name'])
for k in ['raw', 'address_raw']:
splitBlox[i][k] = '\n'.join(splitBlox[i][k])
# search address for City, State and PostCode
apLast = addrsParas[-1].split(',')[-1]
maybeCity = [ap for ap in addrsParas if '–' in ap]
if '–' not in apLast:
splitBlox[i]['State'] = apLast.strip()
if maybeCity:
maybePIN = maybeCity[-1].split('–')[-1].split(',')[0]
maybeCity = maybeCity[-1].split('–')[0].split(',')[-1]
splitBlox[i]['City'] = maybeCity.strip()
splitBlox[i]['PostCode'] = maybePIN.strip()
# add mobile to tel
if 'mobile_raw' in splitBlox[i]:
if 'tel_raw' not in splitBlox[i]:
splitBlox[i]['tel_raw'] = splitBlox[i]['mobile_raw']
else:
splitBlox[i]['tel_raw'] += (', ' + splitBlox[i]['mobile_raw'])
del splitBlox[i]['mobile_raw']
# split tel [as needed]
if 'tel_raw' in splitBlox[i]:
tel_i = [t.strip() for t in splitBlox[i]['tel_raw'].split(',')]
telNum = []
for t in range(len(tel_i)):
if '/' in tel_i[t]:
tns = [t.strip() for t in tel_i[t].split('/')]
tel1 = tns[0]
telNum.append(tel1)
for tn in tns[1:]:
telNum.append(tel1[:-1*len(tn)]+tn)
else:
telNum.append(tel_i[t])
splitBlox[i]['Tel_1'] = telNum[0]
splitBlox[i]['Tel'] = telNum[0] if len(telNum) == 1 else telNum
return splitBlox
(Since I was getting font color anyway, I decided to add another
column called "section" to put East/West/etc in. And I added "PostCode" too, since it seems to be on the other side of "City"...)
Since "raw" is saved, any other value can be double checked manually at least.
The function combines "Mobile" into "Tel" even though they're extracted with separate regex.
I'd say "Tel_1" is fairly reliable, but some of the inconsistent patterns mean that other numbers in "Tel" might come out incorrect if they were separated with '/'.
Also, "Tel" is either a string or a list of strings depending on how many numbers there were in "tel_raw".
After this, you can just view as DataFrame with:
#import docx
#import pandas
content = docx.Document('HE Distributors.docx')
# pandas.DataFrame(splitParas(content.paragraphs)) # <--all Columns
pandas.DataFrame(splitParas(content.paragraphs))[[
'section', 'Name', 'address_raw', 'City',
'PostCode', 'State', 'Email', 'Tel_1', 'tel_raw'
]]
Working on getting some wave heights from websites and my code fails when the wave heights get into the double digit range.
Ex: Currently the code would scrape a 12 from the site as '1' and '2' separately, not '12'.
#Author: David Owens
#File name: soupScraper.py
#Description: html scraper that takes surf reports from various websites
import csv
import requests
from bs4 import BeautifulSoup
NUM_SITES = 2
reportsFinal = []
###################### SURFLINE URL STRINGS AND TAG ###########################
slRootUrl = 'http://www.surfline.com/surf-report/'
slSunsetCliffs = 'sunset-cliffs-southern-california_4254/'
slScrippsUrl = 'scripps-southern-california_4246/'
slBlacksUrl = 'blacks-southern-california_4245/'
slCardiffUrl = 'cardiff-southern-california_4786/'
slTagText = 'observed-wave-range'
slTag = 'id'
#list of surfline URL endings
slUrls = [slSunsetCliffs, slScrippsUrl, slBlacksUrl]
###############################################################################
#################### MAGICSEAWEED URL STRINGS AND TAG #########################
msRootUrl = 'http://magicseaweed.com/'
msSunsetCliffs = 'Sunset-Cliffs-Surf-Report/4211/'
msScrippsUrl = 'Scripps-Pier-La-Jolla-Surf-Report/296/'
msBlacksUrl = 'Torrey-Pines-Blacks-Beach-Surf-Report/295/'
msTagText = 'rating-text'
msTag = 'li'
#list of magicseaweed URL endings
msUrls = [msSunsetCliffs, msScrippsUrl, msBlacksUrl]
###############################################################################
'''
This class represents a surf break. It contains all wave, wind, & tide data
associated with that break relevant to the website
'''
class surfBreak:
def __init__(self, name,low, high, wind, tide):
self.name = name
self.low = low
self.high = high
self.wind = wind
self.tide = tide
#toString method
def __str__(self):
return '{0}: Wave height: {1}-{2} Wind: {3} Tide: {4}'.format(self.name,
self.low, self.high, self.wind, self.tide)
#END CLASS
'''
This returns the proper attribute from the surf report sites
'''
def reportTagFilter(tag):
return (tag.has_attr('class') and 'rating-text' in tag['class']) \
or (tag.has_attr('id') and tag['id'] == 'observed-wave-range')
#END METHOD
'''
This method checks if the parameter is of type int
'''
def representsInt(s):
try:
int(s)
return True
except ValueError:
return False
#END METHOD
'''
This method extracts all ints from a list of reports
reports: The list of surf reports from a single website
returns: reportNums - A list of ints of the wave heights
'''
def extractInts(reports):
print reports
reportNums = []
afterDash = False
num = 0
tens = 0
ones = 0
#extract all ints from the reports and ditch the rest
for report in reports:
for char in report:
if representsInt(char) == True:
num = int(char)
reportNums.append(num)
else:
afterDash = True
return reportNums
#END METHOD
'''
This method iterates through a list of urls and extracts the surf report from
the webpage dependent upon its tag location
rootUrl: The root url of each surf website
urlList: A list of specific urls to be appended to the root url for each
break
tag: the html tag where the actual report lives on the page
returns: a list of strings of each breaks surf report
'''
def extractReports(rootUrl, urlList, tag, tagText):
#empty list to hold reports
reports = []
reportNums = []
index = 0
#loop thru URLs
for url in urlList:
try:
index += 1
#request page
request = requests.get(rootUrl + url)
#turn into soup
soup = BeautifulSoup(request.content, 'lxml')
#get the tag where surflines report lives
reportTag = soup.findAll(reportTagFilter)[0]
reports.append(reportTag.text.strip())
#notify if fail
except:
print 'scrape failure at URL ', index
pass
reportNums = extractInts(reports)
return reportNums
#END METHOD
'''
This method calculates the average of the wave heights
'''
def calcAverages(reportList):
#empty list to hold averages
finalAverages = []
listIndex = 0
waveIndex = 0
#loop thru list of reports to calc each breaks ave low and high
for x in range(0, 6):
#get low ave
average = (reportList[listIndex][waveIndex]
+ reportList[listIndex+1][waveIndex]) / NUM_SITES
finalAverages.append(average)
waveIndex += 1
return finalAverages
#END METHOD
slReports = extractReports(slRootUrl, slUrls, slTag, slTagText)
msReports = extractReports(msRootUrl, msUrls, msTag, msTagText)
reportsFinal.append(slReports)
reportsFinal.append(msReports)
print 'Surfline: ', slReports
print 'Magicseaweed: ', msReports
You are not actually extracting integers, but floats, it seems, since the values in reports are something like ['0.3-0.6 m']. Right now you are just going through every single character and converting them to int one by one or discarding. So no wonder that you will get only single-digit numbers.
One (arguably) simple way to extract those numbers from that string is with regexp:
import re
FLOATEXPR = re.compile("(\d+\.\d)-(\d+\.\d) {0,1}m")
def extractFloats(reports):
reportNums = []
for report in reports:
groups = re.match(FLOATEXPR, report).groups()
for group in groups:
reportNums.append(float(group))
return reportNums
This expression would match your floats and return them as a list.
In detail, the expression will match anything that has at least one digit before a '.', and one digit after it, a '-' between, another float sequence and ending with 'm' or ' m'. Then it groups the parts representing floats to a tuple. For example that ['12.0m-3.0m'] would return [12.0, 3.0]. If you expect it to have more digits after the floating point, you can add an extra '+' after the second 'd':s in the expression.
I wrote some code that grabs the numbers I need from this website, but I don't know what to do next.
It grabs the numbers from the table at the bottom. The ones under calving ease, birth weight, weaning weight, yearling weight, milk and total maternal.
#!/usr/bin/python
import urllib2
from bs4 import BeautifulSoup
import pyperclip
def getPageData(url):
if not ('abri.une.edu.au' in url):
return -1
webpage = urllib2.urlopen(url).read()
soup = BeautifulSoup(webpage, "html.parser")
# This finds the epd tree and saves it as a searchable list
pedTreeTable = soup.find('table', {'class':'TablesEBVBox'})
# This puts all of the epds into a list.
# it looks for anything in pedTreeTable with an td tag.
pageData = pedTreeTable.findAll('td')
pageData.pop(7)
return pageData
def createPedigree(animalPageData):
''' make animalPageData much more useful. Strip the text out and put it in a dict.'''
animals = []
for animal in animalPageData:
animals.append(animal.text)
prettyPedigree = {
'calving_ease' : animals[18],
'birth_weight' : animals[19],
'wean_weight' : animals[20],
'year_weight' : animals[21],
'milk' : animals[22],
'total_mat' : animals[23]
}
for animalKey in prettyPedigree:
if animalKey != 'year_weight' and animalKey != 'dam':
prettyPedigree[animalKey] = stripRegNumber(prettyPedigree[animalKey])
return prettyPedigree
def stripRegNumber(animal):
'''returns the animal with its registration number stripped'''
lAnimal = animal.split()
strippedAnimal = ""
for word in lAnimal:
if not word.isdigit():
strippedAnimal += word + " "
return strippedAnimal
def prettify(pedigree):
''' Takes the pedigree and prints it out in a usable format '''
s = ''
pedString = ""
# this is also ugly, but it was the only way I found to format with a variable
cFormat = '{{:^{}}}'
rFormat = '{{:>{}}}'
#row 1 of string
s += rFormat.format(len(pedigree['calving_ease'])).format(
pedigree['calving_ease']) + '\n'
#row 2 of string
s += rFormat.format(len(pedigree['birth_weight'])).format(
pedigree['birth_weight']) + '\n'
#row 3 of string
s += rFormat.format(len(pedigree['wean_weight'])).format(
pedigree['wean_weight']) + '\n'
#row 4 of string
s += rFormat.format(len(pedigree['year_weight'])).format(
pedigree['year_weight']) + '\n'
#row 4 of string
s += rFormat.format(len(pedigree['milk'])).format(
pedigree['milk']) + '\n'
#row 5 of string
s += rFormat.format(len(pedigree['total_mat'])).format(
pedigree['total_mat']) + '\n'
return s
if __name__ == '__main__':
while True:
url = raw_input('Input a url you want to use to make life easier: \n')
pageData = getPageData(url)
s = prettify(createPedigree(pageData))
pyperclip.copy(s)
if len(s) > 0:
print 'the easy string has been copied to your clipboard'
I've just been using this code for easy copying and pasting. All I have to do is insert the URL, and it saves the numbers to my clipboard.
Now I want to use this code on my website; I want to be able to insert a URL in my HTML code, and it displays these numbers on my page in a table.
My questions are as follows:
How do I use the python code on the website?
How do I insert collected data into a table with HTML?
It sounds like you would want to use something like Django. Although the learning curve is a bit steep, it is worth it and it (of course) supports python.
I'm creating a simple text editor in Python 3.4 and Tkinter. At the moment I'm stuck on the find feature.
I can find characters successfully but I'm not sure how to highlight them. I've tried the tag method without success, error:
str object has no attribute 'tag_add'.
Here's my code for the find function:
def find(): # is called when the user clicks a menu item
findin = tksd.askstring('Find', 'String to find:')
contentsfind = editArea.get(1.0, 'end-1c') # editArea is a scrolledtext area
findcount = 0
for x in contentsfind:
if x == findin:
findcount += 1
print('find - found ' + str(findcount) + ' of ' + findin)
if findcount == 0:
nonefound = ('No matches for ' + findin)
tkmb.showinfo('No matches found', nonefound)
print('find - found 0 of ' + findin)
The user inputs text into a scrolledtext field, and I want to highlight the matching strings on that scrolledtext area.
How would I go about doing this?
Use tag_add to add a tag to a region. Also, instead of getting all the text and searching the text, you can use the search method of the widget. I will return the start of the match, and can also return how many characters matched. You can then use that information to add the tag.
It would look something like this:
...
editArea.tag_configure("find", background="yellow")
...
def find():
findin = tksd.askstring('Find', 'String to find:')
countVar = tk.IntVar()
index = "1.0"
matches = 0
while True:
index = editArea.search(findin, index, "end", count=countVar)
if index == "": break
matches += 1
start = index
end = editArea.index("%s + %s c" % (index, countVar.get()))
editArea.tag_add("find", start, end)
index = end
I am trying to scrape all the different variations of this webpage.For instance the code that should scrape this webpage http://www.virginiaequestrian.com/main.cfm?action=greenpages&sub=view&ID=11849.
should be the same as the code i use to scrape this webpage
http://www.virginiaequestrian.com/main.cfm?action=greenpages&sub=view&ID=11849
def extract_contact(url):
r=requests.get(url)
soup=BeautifulSoup(r.content,'lxml')
tbl=soup.findAll('table')[2]
list=[]
Contact=tbl.findAll('p')[0]
for br in Contact.findAll('br'):
next = br.nextSibling
if not (next and isinstance(next,NavigableString)):
continue
next2 = next.nextSibling
if next2 and isinstance(next2,Tag) and next2.name == 'br':
text = re.sub(r'[\n\r\t\xa0]','',next).replace('Phone:','').strip()
list.append(text)
print list
#Street=list.pop(0)
#CityStateZip=list.pop(0)
#Phone=list.pop(0)
#City,StateZip= CityStateZip.split(',')
#State,Zip= StateZip.split(' ')
#ContactName = Contact.findAll('b')[1]
#ContactEmail = Contact.findAll('a')[1]
#Body=tbl.findAll('p')[1]
#Website = Contact.findAll('a')[2]
#Email = ContactEmail.text.strip()
#ContactName = ContactName.text.strip()
#Website = Website.text.strip()
#Body = Body.text
#Body = re.sub(r'[\n\r\t\xa0]','',Body).strip()
#list.extend([Street,City,State,Zip,ContactName,Phone,Email,Website,Body])
return list
The way i believe i will need to write the code in order it to work, is to set it up so that print list returns the same number of values, ordered identically.Currently, the above script returns these values
[u'2133 Craigs Store Road', u'Afton,VA 22920', u'434-882-3150']
[u'Alexandria,VA 22305']
Accounting for missing values,in order to be able to parse this page consistently,
I need the print list command to return something similar to this
[u'2133 Craigs Store Road', u'Afton,VA 22920', u'434-882-3150']
['',u'Alexandria,VA 22305','']
this way i will be able to manipulate values by position(as they will be in consistent order). The problem is that i don't know how to accomplish this as I am still very new to parsing. If anybody has any insight as to how to solve the problem i would be highly appreciative.
def extract_contact(url):
r=requests.get(url)
soup=BeautifulSoup(r.content,'lxml')
tbl=soup.findAll('table')[2]
list=[]
Contact=tbl.findAll('p')[0]
for br in Contact.findAll('br'):
next = br.nextSibling
if not (next and isinstance(next,NavigableString)):
continue
next2 = next.nextSibling
if next2 and isinstance(next2,Tag) and next2.name == 'br':
text = re.sub(r'[\n\r\t\xa0]','',next).replace('Phone:','').strip()
list.append(text)
Street=[s for s in list if ',' not in s and '-' not in s]
CityStateZip=[s for s in list if ',' in s]
Phone = [s for s in list if '-' in s]
if not Street:
Street=''
else:
Street=Street[0]
if not CityStateZip:
CityStateZip=''
else:
City,StateZip= CityStateZip[0].split(',')
State,Zip= StateZip.split(' ')
if not Phone:
Phone=''
else:
Phone=Phone[0]
list=[]
I figured out an alternative solution using substrings and if statements. Since there are only 3 values max in the list, all with defining characteristics i realized that i could delegate by looking for special characters rather than the position of the record.