write list of paragraph tuples to a csv file - python

The following code is designed to write a tuple, each containing a large paragraph of text, and 2 identifiers behind them, to a single line per each entry.
import urllib2
import json
import csv
base_url = "https://www.eventbriteapi.com/v3/events/search/?page={}
writer = csv.writer(open("./data/events.csv", "a"))
writer.writerow(["description", "category_id", "subcategory_id"])
def format_event(event):
return event["description"]["text"].encode("utf-8").rstrip("\n\r"), event["category_id"], event["subcategory_id"]
for x in range(1, 2):
print "fetching page - {}".format(x)
formatted_url = base_url.format(str(x))
resp = urllib2.urlopen(formatted_url)
data = resp.read()
j_data = json.loads(data)
events = map(format_event, j_data["events"])
for event in events:
#print event
writer.writerow(event)
print "wrote out events for page - {}".format(x)
The ideal format would be to have each line contain a single paragraph, followed by the other fields listed above, yet here is a screenshot of how the data comes out.
If instead I this line to the following:
writer.writerow([event])
Here is how the file now looks:
It certainly looks much closer to what I want, but its got parenthesis around each entry which are undesirable.
EDIT
here is a snippet that contains a sample of the data Im working with.


Can you try writing to the CSV file directly without using using the csv module? You can write/append comma-delimited strings to the CSV file just like writing to typical text files. Also, the way you deal with removing \r and \n characters might not be working. You can use regex to find those characters and replace them with an empty string "":
import urllib2
import json
import re
base_url = "https://www.eventbriteapi.com/v3/events/search/?page={}"
def format_event(event):
ws_to_strip = re.compile(r"(\r|\n)")
description = re.sub(ws_to_strip, "", event["description"]["text"].encode("utf-8"))
return [description, event["category_id"], event["subcategory_id"]]
with open("./data/events.csv", "a") as events_file:
events_file.write(",".join(["description", "category_id", "subcategory_id"]))
for x in range(1, 2):
print "fetching page - {}".format(x)
formatted_url = base_url.format(str(x))
resp = urllib2.urlopen(formatted_url)
data = resp.read()
j_data = json.loads(data)
events = map(format_event, j_data["events"])
for event in events:
events_file.write(",".join(event))
print "wrote out events for page - {}".format(x)


Change your csv writer to be DictWriter.
Make a few tweaks:
def format_event(event):
return {"description": event["description"]["text"].encode("utf-8").rstrip("\n\r"),
"category_id": event["category_id"],
"subcategory_id": event["subcategory_id"]}
May be a few other small things you need to do, but using DictWriter and formatting your data appropriately has been the easiest way to work with csv files that I've found.

Related

Get data from API and save it to txt with Python

I need to get data from this API https://api.storj.io/contacts/f52624d8ef76df81c40853c22f93735581071434 (sample node)
This is my code (python):
import requests
f = requests.get('https://api.storj.io/contacts/f52624d8ef76df81c40853c22f93735581071434')
print f.text
I want to save only protocol, responseTime and reputation in three subsequent lines of the txt file. It's supposed to look something like this::
protocol: 1.2.0
responseTime: 8157.912472694088
reputation: 1377
Unfortunately, I'm stuck at this point and I can not process this data in any way

import requests
f = requests.get('https://api.storj.io/contacts/f52624d8ef76df81c40853c22f93735581071434')
# Store content as json
answer = f.json()
# List of element you want to keep
items = ['protocol', 'responseTime', 'reputation']
# Display
for item in items:
print(item + ':' + str(answer[item]))
# If you want to save in a file
with open("Output.txt", "w") as text_file:
for item in items:
print(item + ':' + str(answer[item]), file=text_file)
Hope it helps! Cheers

You just need to transform to a JSON object to be able to access the keys
import requests
import simplejson as json
f = requests.get('https://api.storj.io/contacts/f52624d8ef76df81c40853c22f93735581071434')
x = json.loads(f.text)
print 'protocol: {}'.format(x.get('protocol'))
print 'responseTime: {}'.format(x.get('responseTime'))
print 'reputation: {}'.format(x.get('reputation'))

This is a very unrefined way to do what you want that you could build off of. You'd need to sub in a path/filename for text.txt.
import requests
import json
f = requests.get('https://api.storj.io/contacts/f52624d8ef76df81c40853c22f93735581071434')
t = json.loads(f.text)
with open('text.txt', 'a') as mfile:
mfile.write("protocol: {0}".format(str(t['protocol'])))
mfile.write("responseTime: {0}".format(str(t['responseTime'])))
mfile.write("reputation: {0}".format(str(t['reputation'])))

How to update line with modified data in Jython?

I'm have a csv file which contains hundred thousands of rows and below are some sample lines..,
1,Ni,23,28-02-2015 12:22:33.2212-02
2,Fi,21,28-02-2015 12:22:34.3212-02
3,Us,33,30-03-2015 12:23:35-01
4,Uk,34,31-03-2015 12:24:36.332211-02
I need to get the last column of csv data which is in wrong datetime format. So I need to get default datetimeformat("YYYY-MM-DD hh:mm:ss[.nnn]") from last column of the data.
I have tried the following script to get lines from it and write into flow file.
import json
import java.io
from org.apache.commons.io import IOUtils
from java.nio.charset import StandardCharsets
from org.apache.nifi.processor.io import StreamCallback
class PyStreamCallback(StreamCallback):
def __init__(self):
pass
def process(self, inputStream, outputStream):
text = IOUtils.readLines(inputStream, StandardCharsets.UTF_8)
for line in text[1:]:
outputStream.write(line + "\n")
flowFile = session.get()
if (flowFile != None):
flowFile = session.write(flowFile,PyStreamCallback())
flowFile = session.putAttribute(flowFile, "filename", flowFile.getAttribute('filename'))
session.transfer(flowFile, REL_SUCCESS)
but I am not able to find a way to convert it like below output.
1,Ni,23,28-02-2015 12:22:33.221
2,Fi,21,29-02-2015 12:22:34.321
3,Us,33,30-03-2015 12:23:35
4,Uk,34,31-03-2015 12:24:36.332
I have checked solutions with my friend(google) and was still not able to find solution.
Can anyone guide me to convert those input data into my required output?

In this transformation the unnecessary data located at the end of each line, so it's really easy to manage transform task with regular expression.
^(.*:\d\d)((\.\d{1,3})(\d*))?(-\d\d)?
Check the regular expression and explanation here:
https://regex101.com/r/sAB4SA/2
As soon as you have a large file - better not to load it into the memory. The following code loads whole the file into the memory:
IOUtils.readLines(inputStream, StandardCharsets.UTF_8)
Better to iterate line by line.
So this code is for ExecuteScript nifi processor with python (Jython) language:
import sys
import re
import traceback
from org.apache.commons.io import IOUtils
from org.apache.nifi.processor.io import StreamCallback
from org.python.core.util import StringUtil
from java.lang import Class
from java.io import BufferedReader
from java.io import InputStreamReader
from java.io import OutputStreamWriter
class TransformCallback(StreamCallback):
def __init__(self):
pass
def process(self, inputStream, outputStream):
try:
writer = OutputStreamWriter(outputStream,"UTF-8")
reader = BufferedReader(InputStreamReader(inputStream,"UTF-8"))
line = reader.readLine()
p = re.compile('^(.*:\d\d)((\.\d{1,3})(\d*))?(-\d\d)?')
while line!= None:
# print line
match = p.search(line)
writer.write( match.group(1) + (match.group(3) if match.group(3)!=None else '') )
writer.write('\n')
line = reader.readLine()
writer.flush()
writer.close()
reader.close()
except:
traceback.print_exc(file=sys.stdout)
raise
flowFile = session.get()
if flowFile != None:
flowFile = session.write(flowFile, TransformCallback())
# Finish by transferring the FlowFile to an output relationship
session.transfer(flowFile, REL_SUCCESS)
And as soon as question is about nifi, here are alternatives that seems to be easier
the same code as above but in groovy for nifi ExecuteScript processor:
def ff = session.get()
if(!ff)return
ff = session.write(ff, {rawIn, rawOut->
// ## transform streams into reader and writer
rawIn.withReader("UTF-8"){reader->
rawOut.withWriter("UTF-8"){writer->
reader.eachLine{line, lineNum->
if(lineNum>1) { // # skip the first line
// ## let use regular expression to transform each line
writer << line.replaceAll( /^(.*:\d\d)((\.\d{1,3})(\d*))?(-\d\d)?/ , '$1$3' ) << '\n'
}
}
}
}
} as StreamCallback)
session.transfer(ff, REL_SUCCESS)
ReplaceText processor
And if regular expression is ok - the easiest way in nifi is a ReplaceText processor that could do regular expression replace line-by-line.
In this case you don't need to write any code, just build the regular expression and configure your processor correctly.

Just using pure jython. It is an example that can be adapted to OP's needs.
Define a datetime parser for this csv file
from datetime import datetime
def parse_datetime(dtstr):
mydatestr='-'.join(dtstr.split('-')[:-1])
try:
return datetime.strptime(mydatestr,'%d-%m-%Y %H:%M:%S.%f').strftime('%d-%m-%Y %H:%M:%S.%f')[:-3]
except ValueError:
return datetime.strptime(mydatestr,'%d-%m-%Y %H:%M:%S').strftime('%d-%m-%Y %H:%M:%S')
my test.csv includes data like this: ( 2015 didnt have 29 Feb had to change OP's example ).
1,Ni,23,27-02-2015 12:22:33.2212-02
2,Fi,21,28-02-2015 12:22:34.3212-02
3,Us,33,30-03-2015 12:23:35-01
4,Uk,34,31-03-2015 12:24:36.332211-02
now the solution
with open('test.csv') as fi:
for line in fi:
line_split=line.split(',')
out_line = ', '.join(word if i<3 else parse_datetime(word) for i,word in enumerate(line_split))
#print(out_line)
#you can write this out_line to a file here.
printing out_line looks like this
1, Ni, 23, 27-02-2015 12:22:33.221
2, Fi, 21, 28-02-2015 12:22:34.321
3, Us, 33, 30-03-2015 12:23:35
4, Uk, 34, 31-03-2015 12:24:36.332

You can get them with regex :
(\d\d-\d\d-\d\d\d\d\ \d\d:\d\d:)(\d+(?:\.\d+)*)(-\d\d)$
Then just replace #2 with a rounded version of #2
See regex example at regexr.com
You could even do it "nicer" by getting every single value with a capturing group and then put them into a datetime.datetime object and print it from there, but imho that would be an overkill in maintainability and loose you too much performance.
Code had no possibility to test
import re
...
pattern = '^(.{25})(\d+(?:\.\d+)*)(-\d\d)$' //used offset for simplicity
....
for line in text[1:]:
match = re.search(pattern, line)
line = match.group(1) + round(match.group(2),3) + match.group(3)
outputStream.write(line + "\n")

Python - Web Scraping - BeautifulSoup & CSV

I am hoping to extract the change in cost of living from one city against many cities. I plan to list the cities I would like to compare in a CSV file and using this list to create the web link that would take me to the website with the information I am looking for.
Here is the link to an example: http://www.expatistan.com/cost-of-living/comparison/phoenix/new-york-city
Unfortunately I am running into several challenges. Any assistance to the following challenges is greatly appreciated!
The output only shows the percentage, but no indication whether it is more expensive or cheaper. For the example listed above, my output based on the current code shows 48%, 129%, 63%, 43%, 42%, and 42%. I tried to correct for this by adding an 'if-statement' to add '+' sign if it is more expensive, or a '-' sign if it is cheaper. However, this 'if-statement' is not functioning correctly.
When I write the data to a CSV file, each of the percentages is written to a new row. I can't seem to figure out how to write it as a list on one line.
(related to item 2) When I write the data to a CSV file for the example listed above, the data is written in the format listed below. How can I correct the format and have the data written in the preferred format listed below (also without the percentage sign)?
CURRENT CSV FORMAT (Note: 'if-statement' not functioning correctly):
City,Food,Housing,Clothes,Transportation,Personal Care,Entertainment
n,e,w,-,y,o,r,k,-,c,i,t,y,-,4,8,%
n,e,w,-,y,o,r,k,-,c,i,t,y,-,1,2,9,%
n,e,w,-,y,o,r,k,-,c,i,t,y,-,6,3,%
n,e,w,-,y,o,r,k,-,c,i,t,y,-,4,3,%
n,e,w,-,y,o,r,k,-,c,i,t,y,-,4,2,%
n,e,w,-,y,o,r,k,-,c,i,t,y,-,4,2,%
PREFERRED CSV FORMAT:
City,Food,Housing,Clothes,Transportation,Personal Care,Entertainment
new-york-city, 48,129,63,43,42,42
Here is my current code:
import requests
import csv
from bs4 import BeautifulSoup
#Read text file
Textfile = open("City.txt")
Textfilelist = Textfile.read()
Textfilelistsplit = Textfilelist.split("\n")
HomeCity = 'Phoenix'
i=0
while i<len(Textfilelistsplit):
url = "http://www.expatistan.com/cost-of-living/comparison/" + HomeCity + "/" + Textfilelistsplit[i]
page = requests.get(url).text
soup_expatistan = BeautifulSoup(page)
#Prepare CSV writer.
WriteResultsFile = csv.writer(open("Expatistan.csv","w"))
WriteResultsFile.writerow(["City","Food","Housing","Clothes","Transportation","Personal Care", "Entertainment"])
expatistan_table = soup_expatistan.find("table",class_="comparison")
expatistan_titles = expatistan_table.find_all("tr",class_="expandable")
for expatistan_title in expatistan_titles:
percent_difference = expatistan_title.find("th",class_="percent")
percent_difference_title = percent_difference.span['class']
if percent_difference_title == "expensiver":
WriteResultsFile.writerow(Textfilelistsplit[i] + '+' + percent_difference.span.string)
else:
WriteResultsFile.writerow(Textfilelistsplit[i] + '-' + percent_difference.span.string)
i+=1

Answers:
Question 1: the class of the span is a list, you need to check if expensiver is inside this list. In other words, replace:
if percent_difference_title == "expensiver"
with:
if "expensiver" in percent_difference.span['class']
Questions 2 and 3: you need to pass a list of column values to writerow(), not string. And, since you want only one record per city, call writerow() outside of the loop (over the trs).
Other issues:
open csv file for writing before the loop
use with context managers while working with files
try to follow PEP8 style guide
Here's the code with modifications:
import requests
import csv
from bs4 import BeautifulSoup
BASE_URL = 'http://www.expatistan.com/cost-of-living/comparison/{home_city}/{city}'
home_city = 'Phoenix'
with open('City.txt') as input_file:
with open("Expatistan.csv", "w") as output_file:
writer = csv.writer(output_file)
writer.writerow(["City", "Food", "Housing", "Clothes", "Transportation", "Personal Care", "Entertainment"])
for line in input_file:
city = line.strip()
url = BASE_URL.format(home_city=home_city, city=city)
soup = BeautifulSoup(requests.get(url).text)
table = soup.find("table", class_="comparison")
differences = []
for title in table.find_all("tr", class_="expandable"):
percent_difference = title.find("th", class_="percent")
if "expensiver" in percent_difference.span['class']:
differences.append('+' + percent_difference.span.string)
else:
differences.append('-' + percent_difference.span.string)
writer.writerow([city] + differences)
For the City.txt containing just one new-york-city line, it produces Expatistan.csv with the following content:
City,Food,Housing,Clothes,Transportation,Personal Care,Entertainment
new-york-city,+48%,+129%,+63%,+43%,+42%,+42%
Make sure you understand what changes have I made. Let me know if you need further help.

csv.writer.writerow() takes a sequence and makes each element a column; normally you'd give it a list with columns, but you are passing in strings instead; that'll add individual characters as columns instead.
Just build a list, then write it to the CSV file.
First, open the CSV file once, not for every separate city; you are clearing out the file every time you open it.
import requests
import csv
from bs4 import BeautifulSoup
HomeCity = 'Phoenix'
with open("City.txt") as cities, open("Expatistan.csv", "wb") as outfile:
writer = csv.writer(outfile)
writer.writerow(["City", "Food", "Housing", "Clothes",
"Transportation", "Personal Care", "Entertainment"])
for line in cities:
city = line.strip()
url = "http://www.expatistan.com/cost-of-living/comparison/{}/{}".format(
HomeCity, city)
resp = requests.get(url)
soup = BeautifulSoup(resp.content, from_encoding=resp.encoding)
titles = soup.select("table.comparison tr.expandable")
row = [city]
for title in titles:
percent_difference = title.find("th", class_="percent")
changeclass = percent_difference.span['class']
change = percent_difference.span.string
if "expensiver" in changeclass:
change = '+' + change
else:
change = '-' + change
row.append(change)
writer.writerow(row)

So, first of all, one passes the writerow method an iterable, and each object in that iterable gets written with commas separating them. So if you give it a string, then each character gets separated:
WriteResultsFile.writerow('hello there')
writes
h,e,l,l,o, ,t,h,e,r,e
But
WriteResultsFile.writerow(['hello', 'there'])
writes
hello,there
That's why you are getting results like
n,e,w,-,y,o,r,k,-,c,i,t,y,-,4,8,%
The rest of your problems are errors in your webscraping. First of all, when I scrape the site, searching for tables with CSS class "comparison" gives me None. So I had to use
expatistan_table = soup_expatistan.find("table","comparison")
Now, the reason your "if statement is broken" is because
percent_difference.span['class']
returns a list. If we modify that to
percent_difference.span['class'][0]
things will work the way you expect.
Now, your real issue is that inside the innermost loop you are finding the % changing in price for the individual items. You want these as items in your row of price differences, not individual rows. So, I declare an empty list items to which I append percent_difference.span.string, and then write the row outside the innermost loop Like so:
items = []
for expatistan_title in expatistan_titles:
percent_difference = expatistan_title.find("th","percent")
percent_difference_title = percent_difference.span["class"][0]
print percent_difference_title
if percent_difference_title == "expensiver":
items.append('+' + percent_difference.span.string)
else:
items.append('-' + percent_difference.span.string)
row = [Textfilelistsplit[i]]
row.extend(items)
WriteResultsFile.writerow(row)
The final error, is the in the while loop you re-open the csv file, and overwrite everything so you only have the final city in the end. Accounting for all theses errors (many of which you should have been able to find without help) leaves us with:
#Prepare CSV writer.
WriteResultsFile = csv.writer(open("Expatistan.csv","w"))
i=0
while i<len(Textfilelistsplit):
url = "http://www.expatistan.com/cost-of-living/comparison/" + HomeCity + "/" + Textfilelistsplit[i]
page = requests.get(url).text
print url
soup_expatistan = BeautifulSoup(page)
WriteResultsFile.writerow(["City","Food","Housing","Clothes","Transportation","Personal Care", "Entertainment"])
expatistan_table = soup_expatistan.find("table","comparison")
expatistan_titles = expatistan_table.find_all("tr","expandable")
items = []
for expatistan_title in expatistan_titles:
percent_difference = expatistan_title.find("th","percent")
percent_difference_title = percent_difference.span["class"][0]
print percent_difference_title
if percent_difference_title == "expensiver":
items.append('+' + percent_difference.span.string)
else:
items.append('-' + percent_difference.span.string)
row = [Textfilelistsplit[i]]
row.extend(items)
WriteResultsFile.writerow(row)
i+=1

YAA - Yet Another Answer.
Unlike the other answers, this treats the data as a series key-value pairs; ie: a list of dictionaries, which are then written to CSV. A list of wanted fields is provided to the csv writer (DictWriter), which discards additional information (beyond the specified fields) and blanks missing information. Also, should the order of the information on the original page change, this solution is unaffected.
I also assume you are going to open the CSV file in something like Excel. Additional parameters need to be given to the csv writer for this to happen nicely (see dialect parameter). Given that we are not sanitising the returned data, we should explicitly delimit it with unconditional quoting (see quoting parameter).
import csv
import requests
from bs4 import BeautifulSoup
#Read text file
with open("City.txt") as cities_h:
cities = cities_h.readlines()
home_city = "Phoenix"
city_data = []
for city in cities:
url = "http://www.expatistan.com/cost-of-living/comparison/%s/%s" % (home_city, city)
resp = requests.get(url)
soup = BeautifulSoup(resp.content, from_encoding = resp.encoding)
titles = soup.select("table.comparison tr.expandable")
if titles:
data = {}
for title in titles:
name = title.find("th", class_ = "clickable")
diff = title.find("th", class_ = "percent")
exp = bool(diff.find("span", class_ = "expensiver"))
data[name.text] = ("+" if exp else "-") + diff.span.text
data["City"] = soup.find("strong", class_ = "city-2").text
city_data.append(data)
with open("Expatistan.csv","w") as csv_h:
fields = \
[
"City",
"Food",
"Housing",
"Clothes",
"Transportation",
"Personal Care",
"Entertainment"
]
#Prepare CSV writer.
writer = csv.DictWriter\
(
csv_h,
fields,
quoting = csv.QUOTE_ALL,
extrasaction = "ignore",
dialect = "excel",
lineterminator = "\n",
)
writer.writeheader()
writer.writerows(city_data)

how to add lists to a dictionary then output to .csv

I'm try to iterate through tables in html by a searchlabel, then update the found value to a dictionary, then write those values to a csv. The output currently works for both the url and the headline, but the name output will either be blank or show "None." If i print the output of blog["name'] however, it is correctly pulling the information I want. I suspect that it's an indentation error but I can't figure out where to line things up. I've tried moving things around but nothing seems to work to get the name assignment to work inside that loop.
import os
from bs4 import BeautifulSoup
import my_csv_writer
def td_finder(tr, searchLabel):
value = ""
index = tr.text.find(searchLabel)
if index>-1:
tds = tr.findAll('td')
if len(tds)>1:
value = tds[1].text
return value
def main():
topdir = 'some_directory'
writer = my_csv_writer.CsvWriter("output.csv")
writer.writeLine(["url", "headline", "name"])
"""Main Function"""
blog = []
for root, dirs, files in os.walk(topdir):
for f in files:
url = os.path.join(root, f)
url = os.path.dirname(url).split('some_file')[1]
if f.lower().endswith((".html")):
file_new = open(os.path.join(root, f), "r").read()
soup = BeautifulSoup(file_new)
blog = {}
#Blog Title
blog["title"] = soup.find('title').text
for table in soup.findAll("table"):
for tr in table.findAll("tr"):
#name
blog["name"] = td_finder(tr, "name:")
seq = [url, unicode(blog["title"]), unicode(blog.get("name"))]
writer.writeLine(seq)
#return ""
if __name__ == '__main__':
main()
print "Finished main"

You're writing unicode strings to a csv file which according to the official docs "The csv module doesn’t directly support reading and writing Unicode...".
It does offer alternative classes to enable different encodings via UnicodeWriter. The following answer from Boud on SO highlights the need to set the desired encoding in the CSV file.

Scraping values from HTML header and saving as a CSV file in Python

All,
I've just started using Python (v 2.7.1) and one of my first programs is trying to scrape information from a website containing power station data using the Standard Library and BeautifulSoup to handle the HTML elements.
The data I'd like to access is obtainable in either the 'Head' section of the HTML or as tables within the main body. The website will generate a CSV file from it data if the CSV link is clicked.
Using a couple of sources on this website I've managed to cobble together the code below which will pull the data out and save it to a file, but, it contains the \n designators. Try as I might, I can't get a correct CSV file to save out.
I am sure it's something simple but need a bit of help if possible!
from BeautifulSoup import BeautifulSoup
import urllib2,string,csv,sys,os
from string import replace
bm_url = 'http://www.bmreports.com/servlet/com.logica.neta.bwp_PanBMDataServlet?param1=T_COTPS-4&param2=&param3=&param4=&param5=2011-02-05&param6=*'
data = urllib2.urlopen(bm_url).read()
soup = BeautifulSoup(data)
data = str(soup.findAll('head',limit=1))
data = replace(data,'[<head>','')
data = replace(data,'<script language="JavaScript" src="/bwx_generic.js"></script>','')
data = replace(data,'<link rel="stylesheet" type="text/css" href="/bwx_style.css" />','')
data = replace(data,'<title>Historic Physical Balancing Mechanism Data</title>','')
data = replace(data,'<script language="JavaScript">','')
data = replace(data,' </script>','')
data = replace(data,'</head>]','')
data = replace(data,'var gs_csv=','')
data = replace(data,'"','')
data = replace(data,"'",'')
data = data.strip()
file_location = 'c:/temp/'
file_name = file_location + 'DataExtract.txt'
file = open(file_name,"wb")
file.write(data)
file.close()

Don't turn it back into a string and then use replace. That completely defeats the point of using BeautifulSoup!
Try starting like this:
scripttag = soup.head.findAll("script")[1]
javascriptdata = scripttag.contents[0]
Then you can use:
partition('=')[2] to cut off the "var gs_csv" bit.
strip(' \n"') to remove unwanted characters at each end (space, newline, ")
replace("\\n","\n") to sort out the new lines.
Incidentally, replace is a string method, so you don't have to import it separately, you can just do data.replace(....
Finally, you need to separate it as csv. You could save it and reopen it, then load it into a csv.reader. You could use the StringIO module to turn it into something you can feed directly to csv.reader (i.e. without saving a file first). But I think this data is simple enough that you can get away with doing:
for line in data.splitlines():
row = line.split(",")

SOLUTION
from BeautifulSoup import BeautifulSoup
import urllib2,string,csv,sys,os,time
bm_url_stem = "http://www.bmreports.com/servlet/com.logica.neta.bwp_PanBMDataServlet?param1="
bm_station = "T_COTPS-3"
bm_param = "&param2=&param3=&param4=&param5="
bm_date = "2011-02-04"
bm_param6 = "&param6=*"
bm_full_url = bm_url_stem + bm_station + bm_param + bm_date + bm_param6
data = urllib2.urlopen(bm_full_url).read()
soup = BeautifulSoup(data)
scripttag = soup.head.findAll("script")[1]
javascriptdata = scripttag.contents[0]
javascriptdata = javascriptdata.partition('=')[2]
javascriptdata = javascriptdata.strip(' \n"')
javascriptdata = javascriptdata.replace("\\n","\n")
javascriptdata = javascriptdata.strip()
csvwriter = csv.writer(file("c:/temp/" + bm_station + "_" + bm_date + ".csv", "wb"))
for line in javascriptdata.splitlines():
row = line.split(",")
csvwriter.writerow(row)
del csvwriter

Categories