def load_answers(self, page):
if not self.valid_url(page.url):
return
paccepted = '//div[@class="answer accepted-answer"]'
panswers = '//div[@class="answer"]'
panswer = '/table/tr/td[@class="answercell"]/div[@class="post-text"]'
xaccepted = engine.Path(paccepted + panswer, link=False)
xanswers = engine.Path(panswers + panswer, link=False)
results = engine.search(page, [xaccepted, xanswers])
self.results = None
raccepted = results[0]
ranswers = results[1]
answers = []
accepted = None
if len(raccepted) > 0:
accepted = etree.tostring(raccepted[0],
method="text",
encoding="UTF-8")
for answer in ranswers:
answers.append(
etree.tostring(answer, method="text", encoding="UTF-8"))
self.results = Answers("unimplemented", accepted, answers)
def load_results(self, page):
xtitle = engine.Path('//h3[@class="r"]/a/text()',link=False)
xlink = engine.Path('//h3[@class="r"]/a/@href')
results = engine.search(page, [xtitle,xlink])
self.titles = []
self.links = []
for t,l in zip(results[0], results[1]):
self.titles.append(t)
self.links.append(l)
def __init__(self, query):
self.base = "https://www.bing.com/images/search"
self.query = query
self.images = []
self.page = None
self.path = engine.Path('//li/div/div[@class="imgpt"]',
children=[
engine.Path('./a/@m', parse=lambda x: loads(x)['murl'])
],
)
def load_wiki(self, page):
if not self.valid_wiki(page.url):
return
pwiki = '//div[@class="mw-parser-output"]/*'
xwiki = engine.Path(pwiki, link=False)
results = engine.search(page, [xwiki])
if len(results) == 0:
return
rwiki = results[0]
wiki = ""
for child in rwiki:
if self.header.match(child.tag):
wiki += "\n"
wiki += "-" * 80
wiki += "\n"
wiki += etree.tostring(child, method="text", encoding="UTF-8")
wiki += "-" * 80
wiki += "\n"
if child.tag.decode("ascii", "ignore") == "p":
wiki += etree.tostring(child, method="text", encoding="UTF-8")
self.wiki = wiki
def load_results(self, page):
xsection = engine.Path('//div[@class="section"]',link=False)
results = engine.search(page, xsection)
if len(results) != 1:
return
self.instruction = etree.tostring(results[0],method="text",encoding="UTF-8")
def load_search(self, page):
if not self.valid_search(page.url):
return
presult = '//div[@class="mw-search-result-heading"]/a'
xresult = engine.Path(presult, link=False)
results = engine.search(page, xresult)
for result in results:
print "UNIMPLEMENTED, ADD SUBTREE TO ENGINE"
print result.attrib['href'], result.attrib['title']
def load_questions(self, page):
if not self.valid_search(page.url):
return
psummary = '//div[@class="summary"]/div[@class="result-link"]'
xsummary = engine.Path(psummary, link=False)
plink = "./span/a/@href"
ptitle = "./span/a/text()"
ptext = "./span"
xtitle = engine.Path(ptitle, link=False)
xlink = engine.Path(plink, link=True)
results = engine.search(page, xsummary)
if len(results) == 0:
writeln("[-] no results found")
return
if not isinstance(self.results, Questions):
self.results = Questions("ERR", [])
for summary in results:
page = engine.Page(page.url, tree=summary)
link = engine.search(page, xlink)
title = engine.search(page, xtitle)
if len(link) == 0 or len(title) == 0:
continue
link = link[0].strip()
title = title[0].strip()[3:]
self.results.questions.append(Question(title, link))
def do_next(self, args):
if not self.page:
writeln("[-] no results loaded!")
return
xpath = engine.Path('//a[@id="pnnext"]/@href')
n = engine.search(self.page, xpath)
if not n:
writeln("[-] no more results!")
return
self.page = engine.Page(n[0], load=True)
self.lpr(self.page)
