def getPageAndStoreResults(self, letter, url, otherPages = True):
htmlPage = Page.get(url)
pageSoup = BeautifulSoup(htmlPage)
# First, get all subnames in this page
subnameSoup = BeautifulSoup("%s" % pageSoup.body.find_all(self.getsubnameDiv)).find_all("a")
# And bufferize them all
for entry in subnameSoup:
# If we are on the entry limit, stop process
if self.entryLimit > 0 and len(self._subnameList) >= self.entryLimit:
break
subname = entry.string
if subname not in self._subnameList:
self._subnameList += (subname, )
print "Collected %d entries for letter %s - Total collected: %d" % (len(subnameSoup), letter, len(self._subnameList))
if otherPages == True:
# Second, seek other pages
otherPagesSoup = BeautifulSoup("%s" %
BeautifulSoup("%s" %
pageSoup.find_all("div", {"class":"span11"})
).find_all(self.getsubnamePaginationDiv)
).find_all("a")
for entry in otherPagesSoup:
# If we are on the entry limit, stop process
if self.entryLimit > 0 and len(self._subnameList) >= self.entryLimit:
break
if not re.search("%s-1.html" % letter, entry["href"]):
self.getPageAndStoreResults(letter, "%s/%s" % (self.rootURL, entry["href"]), False)
def getPageAndStoreResults(self, pageId, getRange=True):
htmlPage = Page.get("%s-%d" % (self.baseURL, pageId))
pageSoup = BeautifulSoup(htmlPage)
# on genealogie.com we need to find how many pages of names we have
if self.lastPageId == -1:
paginationSoup = BeautifulSoup("%s" % pageSoup.body.find_all("div", {"class": "pageNo"})).find_all("a")
self.lastPageId = int(re.sub("\n","",re.sub(" ","",paginationSoup[-1].string)))
nameSoup = pageSoup.find_all("label", {"class":"nameValue"})
for entry in nameSoup:
# If we are on the entry limit, stop process
if self.entryLimit > 0 and len(self._nameList) >= self.entryLimit:
break
# We get the first <a> element, it's the name label
entrySoup = BeautifulSoup("%s" %
BeautifulSoup("%s" % entry).find_all("a")[-1]
)
for entry2 in entrySoup:
tmpName = "%s" % re.sub("\n","", re.sub(" ","",entry2.string))
if tmpName not in self._nameList:
self._nameList += (tmpName,)
print "Current ID %d - Total Collected Names %d" % (pageId, len(self._nameList))
# If page is page 1, then we loop the results
if getRange == True:
for pId in range(2, self.lastPageId+1):
# If we are on the entry limit, stop process
if self.entryLimit > 0 and len(self._nameList) >= self.entryLimit:
break
self.getPageAndStoreResults(pId, False)
