def extract_user_info(doc):
try:
scripts = util.extract_script(doc)
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__63"'
)
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__62"'
)
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__61"'
)
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__59"'
)
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
lis = html.xpath(r'//ul/li')
info = []
for li in lis:
text = li.xpath("string()")
info.append(util.clean_text(text))
level_info = extract_level_info(doc)
if level_info:
info.append(level_info)
return info
except:
traceback.print_exc()
return None
def extract_user_info(doc):
try:
scripts = util.extract_script(doc)
script = util.select_script(scripts,
r'"domid":"Pl_Official_PersonalInfo__63"')
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__62"')
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__61"')
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__59"')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
lis = html.xpath(r'//ul/li')
info = []
for li in lis:
text = li.xpath("string()")
info.append(util.clean_text(text))
level_info = extract_level_info(doc)
if level_info:
info.append(level_info)
return info
except:
traceback.print_exc()
return None
def extract_hot_weibo(doc):
try:
scripts = util.extract_script(doc)
print len(scripts)
script = util.select_script(scripts,
r'"domid":"Pl_Core_NewMixFeed__3"')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
divs = html.xpath('//div[@action-type="feed_list_item"]')
weibos = []
for div in divs:
try:
weibo = Weibo()
weibo["mid"] = div.attrib.get("mid")
_div = div.xpath('.//a[@class="W_texta W_fb"]')[0]
usercard = _div.attrib.get("usercard")
end = usercard.index("&")
weibo["uid"] = usercard[len("id="):end]
link = div.xpath('.//*[@class="feed_from W_textb"]/a')[0]
weibo["url"] = link.attrib.get("href")
extract_content(div, weibo)
extract_date_source(div, weibo)
weibos.append(weibo)
except:
traceback.print_exc()
return weibos
except:
traceback.print_exc()
def extract_searched_weibo(doc, page_num=None):
try:
scripts = util.extract_script(doc)
script = util.select_script(scripts, r'"pid":"pl_weibo_direct"')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
divs = html.xpath('//div[@action-type="feed_list_item"]')
weibos = []
for div in divs:
try:
weibo = Weibo()
weibo["mid"] = div.attrib.get("mid")
_div = div.xpath('.//a[@class="W_texta W_fb"]')[0]
usercard = _div.attrib.get("usercard")
end = usercard.index("&")
weibo["uid"] = usercard[len("id="):end]
weibos.append(weibo)
except:
traceback.print_exc()
if page_num:
try:
lis = html.xpath(r'//span[@class="list"]/div/ul/li')
text = lis[-1].xpath(".//text()")[0]
total = int(text[1:-1])
return weibos, total
except:
return weibos, 1
else:
return weibos
except:
if page_num:
return None, None
else:
return None
def extract_search_result_count(doc):
scripts = util.extract_script(doc)
script = util.select_script(scripts, r'"pid":"pl_weibo_direct"')
text = script.text.strip()
text = text.encode("utf-8", "ignore")
print text
p = re.compile("找到(\d+)条结果")
print p.search(text)
def extract_content_html(self, html):
"""
Extracting html code that contains weibo content.
"""
scripts = util.extract_script(html)
script = util.select_script(scripts, r'pl.content.homefeed.index')
text = script.text.strip()
return util.extract_html_from_script(text)
def extract_content_html(self, html, single=False):
"""
Extracting html code that contains weibo content.
"""
scripts = util.extract_script(html)
if not single:
script = util.select_script(
scripts, r'"domid":"Pl_Official_MyProfileFeed'
)
if not script:
script = util.select_script(
scripts, r'"domid":"v6_pl_content_homefeed"'
)
else:
script = util.select_script(
scripts, r'pl.content.weiboDetail.index'
)
text = script.text.strip()
return util.extract_html_from_script(text)
def extract_content_html(self, html, single=False, hot=False):
"""
Extracting html code that contains weibo content.
"""
scripts = util.extract_script(html)
if hot:
script = util.select_script(scripts,
r'"domid":"Pl_Core_NewMixFeed__3"')
elif not single:
script = util.select_script(scripts,
r'"domid":"Pl_Official_MyProfileFeed')
if not script:
script = util.select_script(
scripts, r'"domid":"v6_pl_content_homefeed"')
else:
script = util.select_script(scripts,
r'pl.content.weiboDetail.index')
text = script.text.strip()
return util.extract_html_from_script(text)
def extract_content_html(self, html):
"""
Extracting html code that contains weibo content.
"""
scripts = util.extract_script(html)
script = util.select_script(
scripts, r'pl.content.homefeed.index'
)
text = script.text.strip()
return util.extract_html_from_script(text)
def extract_topic(doc):
scripts = util.extract_script(doc)
script = util.select_script(scripts, '"domid":"v6_pl_rightmod_recominfo"')
text = script.text.strip()
doc = util.extract_html_from_script(text)
html = etree.HTML(doc)
links = html.xpath('//ul[@class="hot_topic"]/li//a')
topics = []
for link in links:
topics.append((link.attrib["href"], link.text.strip()))
return topics
def extract_topic(doc):
scripts = util.extract_script(doc)
script = util.select_script(scripts, '"domid":"v6_pl_rightmod_recominfo"')
text = script.text.strip()
doc = util.extract_html_from_script(text)
html = etree.HTML(doc)
links = html.xpath('//ul[@class="hot_topic"]/li//a')
topics = []
for link in links:
topics.append((link.attrib["href"], link.text.strip()))
return topics
def extract_level_info(doc):
try:
scripts = util.extract_script(doc)
script = util.select_script(scripts,
r'"domid":"Pl_Official_RightGrowNew')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
p = html.xpath(r'//p[@class="level_info"]')
if p:
text = p[0].xpath("string()")
info = util.clean_text(text)
return info
except:
traceback.print_exc()
return None
def extract_level_info(doc):
try:
scripts = util.extract_script(doc)
script = util.select_script(
scripts, r'"domid":"Pl_Official_RightGrowNew'
)
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
p = html.xpath(r'//p[@class="level_info"]')
if p:
text = p[0].xpath("string()")
info = util.clean_text(text)
return info
except:
traceback.print_exc()
return None
def extract_relation(doc):
scripts = util.extract_script(doc)
script = util.select_script(scripts, r'pl.content.followTab.index')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
datas = html.xpath(r'.//ul[@class="follow_list"]/li/@action-data')
for data in datas:
try:
followee = {}
splits = data.split("&")
for split in splits:
_splits = split.split("=")
followee[_splits[0]] = _splits[1]
yield followee
except:
traceback.print_exc()
continue
def extract_relation(doc):
scripts = util.extract_script(doc)
script = util.select_script(scripts, r'pl.content.followTab.index')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
datas = html.xpath(r'.//ul[@class="follow_list"]/li/@action-data')
for data in datas:
try:
followee = {}
splits = data.split("&")
for split in splits:
_splits = split.split("=")
followee[_splits[0]] = _splits[1]
yield followee
except:
traceback.print_exc()
continue
def extract_inbox_comment(data):
comments = []
try:
scripts = util.extract_script(data)
script = util.select_script(scripts,
r'"domid":"v6_pl_content_commentlist"')
text = script.text.strip()
doc = util.extract_html_from_script(text)
html = etree.HTML(doc)
divs = html.xpath('//div[@node-type="feed_commentList_comment"]')
except:
return comments
for div in divs:
try:
weibo_url, comment = extract_individual_comment(div)
comments.append((weibo_url, comment))
except:
pass
return comments
def extract_user(doc, page_num=None):
try:
scripts = util.extract_script(doc)
script = util.select_script(scripts, r'"pid":"pl_user_feedList"')
json_data = re.findall("\(({.*})\)", script.text)[0]
json_data = json.loads(json_data)
html = etree.HTML(json_data["html"])
divs = html.xpath(r'//div[@class="list_person clearfix"]')
users = []
for div in divs:
try:
user = {}
detail = div.xpath(r'.//div[@class="person_detail"]')[0]
_as = detail.xpath(r'.//p[@class="person_name"]/a')
if len(_as) >= 1:
user["uid"] = _as[0].attrib.get("uid")
user["nick"] = _as[0].attrib.get("title")
user["home_url"] = _as[0].attrib.get("href")
if len(_as) > 1:
if _as[1].attrib.get("alt") is not None:
user["verify"] = _as[1].attrib.get("alt")
users.append(user)
except:
traceback.print_exc()
continue
if page_num:
try:
lis = html.xpath(r'//span[@class="list"]/div/ul/li')
text = lis[-1].xpath(".//text()")[0]
total = int(text[1:-1])
return users, total
except:
return users, 1
else:
return users
except:
if page_num:
return None, None
else:
return None
def extract_user(doc, page_num=None):
try:
scripts = util.extract_script(doc)
script = util.select_script(scripts, r'"pid":"pl_user_feedList"')
json_data = re.findall("\(({.*})\)", script.text)[0]
json_data = json.loads(json_data)
html = etree.HTML(json_data["html"])
divs = html.xpath(r'//div[@class="list_person clearfix"]')
users = []
for div in divs:
try:
user = {}
detail = div.xpath(r'.//div[@class="person_detail"]')[0]
_as = detail.xpath(r'.//p[@class="person_name"]/a')
if len(_as) >= 1:
user["uid"] = _as[0].attrib.get("uid")
user["nick"] = _as[0].attrib.get("title")
user["home_url"] = _as[0].attrib.get("href")
if len(_as) > 1:
if _as[1].attrib.get("alt") is not None:
user["verify"] = _as[1].attrib.get("alt")
users.append(user)
except:
traceback.print_exc()
continue
if page_num:
try:
lis = html.xpath(r'//span[@class="list"]/div/ul/li')
text = lis[-1].xpath(".//text()")[0]
total = int(text[1:-1])
return users, total
except:
return users, 1
else:
return users
except:
if page_num:
return None, None
else:
return None
def extract_inbox_comment(data):
comments = []
try:
scripts = util.extract_script(data)
script = util.select_script(
scripts, r'"domid":"v6_pl_content_commentlist"'
)
text = script.text.strip()
doc = util.extract_html_from_script(text)
html = etree.HTML(doc)
divs = html.xpath('//div[@node-type="feed_commentList_comment"]')
except:
return comments
for div in divs:
try:
weibo_url, comment = extract_individual_comment(div)
comments.append((weibo_url, comment))
except:
pass
return comments
def extract_searched_weibo(doc, page_num=None):
try:
scripts = util.extract_script(doc)
script = util.select_script(scripts, r'"pid":"pl_weibo_direct"')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
divs = html.xpath('//div[@action-type="feed_list_item"]')
weibos = []
for div in divs:
try:
weibo = Weibo()
weibo["mid"] = div.attrib.get("mid")
_div = div.xpath('.//a[@class="W_texta W_fb"]')[0]
usercard = _div.attrib.get("usercard")
end = usercard.index("&")
weibo["uid"] = usercard[len("id="):end]
link = div.xpath('.//*[@class="feed_from W_textb"]/a')[0]
weibo["url"] = link.attrib.get("href")
extract_content(div, weibo)
extract_date_source(div, weibo)
weibos.append(weibo)
except:
traceback.print_exc()
if page_num:
try:
lis = html.xpath(r'//span[@class="list"]/div/ul/li')
text = lis[-1].xpath(".//text()")[0]
total = int(text[1:-1])
return weibos, total
except:
return weibos, 1
else:
return weibos
except:
if page_num:
return None, None
else:
return None