Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
a1f00eb
commit 9df66b3
Showing
1 changed file
with
52 additions
and
23 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,24 +1,53 @@ | ||
# This is a template for a Python scraper on morph.io (https://morph.io) | ||
# including some code snippets below that you should find helpful | ||
# #import the libraries containing our functions | ||
import scraperwiki | ||
import lxml.html | ||
import urllib | ||
#Use the urllib.urlopen function to open the URL 'properly' so it works | ||
horselinkurl = urllib.urlopen('http://www.horsedeathwatch.com/'+table_cellsurls[0].attrib.\ | ||
get('href')).read() | ||
# scrape_table function: gets passed an individual page to scrape | ||
def scrape_table(elephant): | ||
rows = elephant.cssselect("tr") # selects all <tr> blocks | ||
for row in rows: | ||
# Set up our data record - we'll need it later | ||
record = {} | ||
table_cells = row.cssselect("td") | ||
#if there's anything in the table_cells variable (a list) | ||
if table_cells: | ||
#add to the variable record (a dictionary) these pairs: label 'artist': the text in the first [0] table_cells item... | ||
record['Horse'] = table_cells[0].text_content() | ||
#create variable ‘table_cellsurls’ and put in it any links within the first table_cells item | ||
table_cellsurls = table_cells[0].cssselect("a") | ||
#grab the href=†attribute and put that in ‘HorseURL’ | ||
record['HorseURL'] = table_cellsurls[0].attrib.get('href') | ||
testingreplace = 'http://www.horsedeathwatch.com/'+table_cellsurls[0].attrib.get('href') | ||
print testingreplace.replace(" ", "%20") | ||
horselink = testingreplace.replace(" ", "%20") | ||
horsehtml = scraperwiki.scrape(horselink) | ||
#Turn the webpage string into an lxml object | ||
horseroot = lxml.html.fromstring(horsehtml) | ||
#put all the <p> tags on the horse page into a list | ||
pars = horseroot.cssselect("p") | ||
#print and then store the text_content for the first item <p> in the pars list, the Age | ||
print pars[0].text_content() | ||
record['Agetest2'] = pars[0].text_content() | ||
record['Date'] = table_cells[1].text | ||
record['Course'] = table_cells[2].text | ||
#... label 'sales m': the text in the fifth [4] table_cells item... | ||
record['Cause of death'] = table_cells[3].text | ||
# Print out the data we've gathered into the record variable, followed by '-----' | ||
print record, '------------' | ||
# Finally, save the record to the datastore - 'Artist' is our unique key | ||
scraperwiki.sqlite.save(["Horse"], record) | ||
|
||
# scrape_and_look_for_next_link function: calls the scrape_table | ||
# function, then hunts for a 'next' link: if one is found, calls itself again | ||
def scrape_and_look_for_next_link(url): | ||
html = scraperwiki.scrape(url) | ||
print html | ||
root = lxml.html.fromstring(html) | ||
scrape_table(root) | ||
|
||
# import scraperwiki | ||
# import lxml.html | ||
# | ||
# # Read in a page | ||
# html = scraperwiki.scrape("http://foo.com") | ||
# | ||
# # Find something on the page using css selectors | ||
# root = lxml.html.fromstring(html) | ||
# root.cssselect("div[align='left']") | ||
# | ||
# # Write out to the sqlite database using scraperwiki library | ||
# scraperwiki.sqlite.save(unique_keys=['name'], data={"name": "susan", "occupation": "software developer"}) | ||
# | ||
# # An arbitrary query against the database | ||
# scraperwiki.sql.select("* from data where 'name'='peter'") | ||
|
||
# You don't have to do things with the ScraperWiki and lxml libraries. | ||
# You can use whatever libraries you want: https://morph.io/documentation/python | ||
# All that matters is that your final data is written to an SQLite database | ||
# called "data.sqlite" in the current working directory which has at least a table | ||
# called "data". | ||
# START HERE: define your starting URL - then call a function to scrape it | ||
starting_url = 'http://www.horsedeathwatch.com/' | ||
scrape_and_look_for_next_link(starting_url) |