def scrapeMain():
for r in conf["scraper"]["queries"]:
name = r["name"]
page = r["page"]
rules = r["rules"]
replace = r["replace"]
txtFilename = name + ".txt"
ignore = conf["scraper"]["ignore"]
url = conf["scraper"]["url"] + page
begin = conf["scraper"]["pageBegin"]
end = conf["scraper"]["pageEnd"]
search = conf["scraper"]["searchTerm"]
delim = conf["scraper"]["delim"]
squash = conf["scraper"]["squash"]
founds, pages = spidey.crawl(url, begin, end, search, delim, squash, txtFilename)
print("Found: " + str(founds) + " results on " + str(pages) + " pages")
print("Cleaning " + txtFilename)
total, first, last = spidey.cleanResults(txtFilename, rules, replace, ignore)
print("Captured " + str(total) + " results from " + first + " to " + last)
print("Done!")
def scrapeMain():
for r in conf['scraper']['queries']:
name = r['name']
page = r['page']
rules = r['rules']
replace = r['replace']
txtFilename = name + '.txt'
ignore = conf['scraper']['ignore']
url = conf['scraper']['url'] + page
begin = conf['scraper']['pageBegin']
end = conf['scraper']['pageEnd']
search = conf['scraper']['searchTerm']
delim = conf['scraper']['delim']
squash = conf['scraper']['squash']
founds, pages = spidey.crawl(url, begin, end, search, delim, squash, txtFilename)
print('Found: ' + str(founds) + ' results on ' + str(pages) + ' pages')
print('Cleaning ' + txtFilename)
total, first, last = spidey.cleanResults(txtFilename, rules, replace, ignore)
print('Captured ' + str(total) + ' results from ' + first + ' to ' + last)
print('Done!')
def scrapeDeps():
print("Sorting deprecations...")
depFilename = "LSL_DEPRECATED.txt"
depFilename2 = "LSL_DEPRECATED2.txt"
try:
os.remove(depFilename)
os.remove(depFilename2)
except:
pass
# First search, on LSL_FUNCTIONS page
searchTerm = "<s>"
pageBegin = 'title="LlAbs"'
pageEnd = 'id="footnote_1"'
delim = [">", "<"]
ignore = ["\n", "(", "(previous 200) (", "next 200", "previous 200", "(previous 200) (next 200)\n"]
url = "http://wiki.secondlife.com/w/index.php?title=Category:LSL_Functions"
spidey.crawl(url, pageBegin, pageEnd, searchTerm, delim, [], depFilename)
spidey.cleanResults(depFilename, ["firstLower"], [False], ignore)
# Second search, on the ill-maintained LSL_DEPRECATED page
url = "http://wiki.secondlife.com/w/index.php?title=Category:LSL_Deprecated"
pageBegin = "Pages in category"
pageEnd = 'class="printfooter"'
searchTerm = '<li><a href="/wiki/'
ignore = ["\n", "(", "(previous 200) (", "next 200", "previous 200", "(previous 200) (next 200)\n"]
spidey.crawl(url, pageBegin, pageEnd, searchTerm, delim, [], depFilename2)
spidey.cleanResults(depFilename, [False], [" ", "_"], ignore)
# Merge the two dep files
depFile1 = open(depFilename, "r")
depFile2 = open(depFilename2, "r")
deps1 = depFile1.read().splitlines()
# debug- print(str(deps1))
deps2 = []
for line in depFile2:
line = line.strip("\n")
if line[0:2] == "Ll":
line = "ll" + line[2:]
if not line in deps1:
if line != "\\n":
deps2.append(line.strip("\n"))
deps2Txt = "\n".join(deps2)
depFile1.close
depFile2.close
depFile1 = open(depFilename, "a")
depFile1.write(deps2Txt)
depFile1.close
# Remove deps from captured result files case insensitively
depFile = open(depFilename, "r")
for r in conf["scraper"]["queries"]:
srcFilename = r["name"] + ".txt"
srcFile = open(srcFilename, "r")
src = []
for line in srcFile:
src.append(line.strip("\n"))
for dep in depFile:
dep = dep.strip("\n")
try:
src.remove(dep)
except:
pass
print("Removing deprecation from: " + srcFilename + ": " + dep)
srcTxt = "\n".join(src)
srcFile.close
srcFile = open(srcFilename, "w")
srcFile.write(srcTxt)
srcFile.close
depFile.close
print("Done!")
def scrapeDeps():
print('Sorting deprecations...')
depFilename = 'LSL_DEPRECATED.txt'
depFilename2 = 'LSL_DEPRECATED2.txt'
try:
os.remove(depFilename)
os.remove(depFilename2)
except:
pass
# First search, on LSL_FUNCTIONS page
searchTerm = '<s>'
pageBegin = 'title="LlAbs"'
pageEnd = 'id="footnote_1"'
delim = ['>','<']
ignore = ['\n', '(', '(previous 200) (', 'next 200', 'previous 200', '(previous 200) (next 200)\n']
url = 'http://wiki.secondlife.com/w/index.php?title=Category:LSL_Functions'
spidey.crawl(url, pageBegin, pageEnd, searchTerm, delim, [], depFilename)
spidey.cleanResults(depFilename, ['firstLower'], [False], ignore)
# Second search, on the ill-maintained LSL_DEPRECATED page
url = 'http://wiki.secondlife.com/w/index.php?title=Category:LSL_Deprecated'
pageBegin = 'Pages in category'
pageEnd = 'class="printfooter"'
searchTerm = '<li><a href="/wiki/'
ignore = ['\n', '(', '(previous 200) (', 'next 200', 'previous 200', '(previous 200) (next 200)\n']
spidey.crawl(url, pageBegin, pageEnd, searchTerm, delim, [], depFilename2)
spidey.cleanResults(depFilename, [False], [' ','_'], ignore)
# Merge the two dep files
depFile1 = open(depFilename, 'r')
depFile2 = open(depFilename2, 'r')
deps1 = depFile1.read().splitlines()
# debug- print(str(deps1))
deps2 = []
for line in depFile2:
line = line.strip('\n')
if line[0:2] == 'Ll':
line = 'll' + line[2:]
if not line in deps1:
if line != '\\n':
deps2.append(line.strip('\n'))
deps2Txt = '\n'.join(deps2)
depFile1.close
depFile2.close
depFile1 = open(depFilename, 'a')
depFile1.write(deps2Txt)
depFile1.close
# Remove deps from captured result files case insensitively
depFile = open(depFilename, 'r')
for r in conf['scraper']['queries']:
srcFilename = r['name'] + '.txt'
srcFile = open(srcFilename, 'r')
src = []
for line in srcFile:
src.append(line.strip('\n'))
for dep in depFile:
dep = dep.strip('\n')
try:
src.remove(dep)
except: pass
print('Removing deprecation from: ' + srcFilename + ': ' + dep)
srcTxt = '\n'.join(src)
srcFile.close
srcFile = open(srcFilename, 'w')
srcFile.write(srcTxt)
srcFile.close
depFile.close
print('Done!')
