def main():
""""""
mainUrl = "http://events.cnbloggercon.org/event/cnbloggercon2007/"
content = Page(mainUrl).Content
soup = BeautifulSoup(content)
links = soup("a")
peopleList = []
for item in links:
href = item["href"]
if href.lower()[:8] == "/people/":
peopleList.append("http://events.cnbloggercon.org" + href + "profile/")
pageLink = []
for link in peopleList:
print link
ct = Page(str(link.encode("utf-8")).lower()).Content
pos = ct.find("个人网站")
if pos == -1:
continue
ct = ct[pos:]
so = BeautifulSoup(ct)
fLink = so("a")[0]["href"]
pageLink.append(fLink)
f = file("abcde.txt", "w")
for i in pageLink:
f.write(i)
f.write("\r\n")
def get(self, slug): page = Page.find(slug=slug)[0] page.content = "This is the content" page.save() return repr(page)
def get_page(year, month, day, slug):
def match(page):
date = page.date()
return date.year == year and date.month == month \
and date.day == day and page.slug() == slug
return Page.find(match)