def parse(page):
try:
t = eparse(page)
except lxml.etree.ParserError:
print sys.stderr, "page content error"
return info
info = {}
def parse(page):
try:
t=eparse(page)
except lxml.etree.ParserError:
print sys.stderr, "page content error"
return info
info = {}
def parse_csdn(page):
try:
t = eparse(page)
except lxml.etree.ParserError:
print sys.stderr, "page content error"
return info
r = []
sel = []
find = t.cssselect('div[class="per_dynamic"]')
if find:
titles = find[0].xpath('//a[contains(@href,"http:")]')
for li in titles:
r.append(li.text_content().strip().replace('\n', ' '))
print "======", r
sel2 = t.cssselect('div[class="position education vevent vcard"]')
for li in sel2:
sel.append(li)
for li in sel:
item = {}
find = li.cssselect('h3[class="summary fn org"]')
if find:
item['school'] = find[0].text_content().strip().replace('\n', ' ')
find = li.cssselect('span[class="degree"]')
if find:
item['degree'] = find[0].text_content().strip().replace('\n', ' ')
find = li.cssselect('span[class="major"]')
if find:
item['major'] = find[0].text_content().strip().replace('\n', ' ')
find = li.cssselect('abbr[class="dtstart"]')
if find:
item['dtstart'] = find[0].text_content().strip().replace('\n', ' ')
find = li.cssselect('abbr[class="dtstamp"]')
if find:
item['dtend'] = find[0].text_content().strip().replace('\n', ' ')
find = li.cssselect('abbr[class="dtend"]')
if find:
item['dtend'] = find[0].text_content().strip().replace('\n', ' ')
find = li.cssselect('p[class=" desc details-education"]')
if find:
item['desc'] = find[0].text_content().strip().replace('\n', ' ')
find = li.cssselect('p[class="desc details-education"]')
if find:
item['activities'] = find[0].text_content().strip().replace(
'\n', ' ')
r.append(item)
return r
def parse(page):
info = {}
try:
t=eparse(page)
except lxml.etree.ParserError:
print sys.stderr, "page content error"
return info
info = parse_profile(t)
dynamic = parse_dynamic(t)
info['dynamic'] = dynamic
return info
def parse_dir(t):
r = []
try:
t=eparse(page)
except lxml.etree.ParserError:
print sys.stderr, "page content error"
return r
sel = t.cssselect('h2 strong a')
for li in sel:
r.append(li.attrib['href'])
return r
def parse_csdn(page):
try:
t=eparse(page)
except lxml.etree.ParserError:
print sys.stderr, "page content error"
return info
r = []
sel = []
find = t.cssselect('div[class="per_dynamic"]')
if find:
titles = find[0].xpath('//a[contains(@href,"http:")]')
for li in titles:
r.append(li.text_content().strip().replace('\n',' '))
print "======",r
sel2 = t.cssselect('div[class="position education vevent vcard"]')
for li in sel2:
sel.append(li)
for li in sel:
item = {}
find = li.cssselect('h3[class="summary fn org"]')
if find:
item['school'] = find[0].text_content().strip().replace('\n',' ')
find = li.cssselect('span[class="degree"]')
if find:
item['degree'] = find[0].text_content().strip().replace('\n',' ')
find = li.cssselect('span[class="major"]')
if find:
item['major'] = find[0].text_content().strip().replace('\n',' ')
find = li.cssselect('abbr[class="dtstart"]')
if find:
item['dtstart'] = find[0].text_content().strip().replace('\n',' ')
find = li.cssselect('abbr[class="dtstamp"]')
if find:
item['dtend'] = find[0].text_content().strip().replace('\n',' ')
find = li.cssselect('abbr[class="dtend"]')
if find:
item['dtend'] = find[0].text_content().strip().replace('\n',' ')
find = li.cssselect('p[class=" desc details-education"]')
if find:
item['desc'] = find[0].text_content().strip().replace('\n',' ')
find = li.cssselect('p[class="desc details-education"]')
if find:
item['activities'] = find[0].text_content().strip().replace('\n',' ')
r.append(item)
return r
def parse(page):
info = {}
try:
t=eparse(page)
except lxml.etree.ParserError:
print sys.stderr, "page content error"
return info
info = parse_addition(t)
work = parse_work(t)
info['work'] = work
edu = parse_edu(t)
info['edu'] = edu
return info
def parse(page):
info = {}
try:
t = eparse(page)
except lxml.etree.ParserError:
print sys.stderr, "page content error"
return info
info = parse_addition(t)
work = parse_work(t)
info['work'] = work
edu = parse_edu(t)
info['edu'] = edu
return info