def get_citys():
'''
获取城市
'''
try:
html = rq.get_cookie(__city_url)
except Exception, e:
print e
return
def getArticle(offset):
'''
获取文章列表
'''
print u'页码：%s' % offset
url = 'http://mp.weixin.qq.com/mp/profile_ext?action=getmsg&__biz=' + biz + '&f=json&offset=' + str(
offset) + '&count=10&f=json'
dataStr = rq.get_cookie(url, cookie_file_name="wx")
# print dataStr
dataJson = json.loads(dataStr)
if dataJson["errmsg"] != 'ok':
print u'获取数据返回:%s' % dataJson["errmsg"]
return
next_offset = dataJson["next_offset"]
# 文章列表
if offset == next_offset:
print u'已经是没有翻页数据'
return
general_msg_list_str = dataJson["general_msg_list"]
general_msg_list_json = json.loads(general_msg_list_str)
article_list = general_msg_list_json["list"]
# print article_list
for item in article_list:
# 获取文章发布时间
publish_timestamp = item['comm_msg_info']['datetime']
publish_time = time.localtime(publish_timestamp)
# 校验文章发布时间
if publish_time.tm_year < 2017:
print u'超过限定日期，不继续捕获分页数据'
return
if not item.has_key('app_msg_ext_info'):
continue
# 文章标题
item_title = item['app_msg_ext_info']['title']
# 文章地址
item_url = item['app_msg_ext_info']['content_url']
# 获主文章
articleDatas.append({
'title': item_title,
'url': item_url,
'time': time.strftime("%Y-%m-%d", publish_time)
})
if item['app_msg_ext_info']['multi_app_msg_item_list'] is None:
continue
# 子文章
for multi_item in item['app_msg_ext_info']['multi_app_msg_item_list']:
item_title = multi_item['title']
item_url = multi_item['content_url']
articleDatas.append({
'title': item_title,
'url': item_url,
'time': time.strftime("%Y-%m-%d", publish_time)
})
# 延迟
hp.sleep(1, 3)
getArticle(next_offset)
def getCommetDatas(url):
'''
获取评论JSON数据
* 'url' 文章地址
'''
try:
htmlStr = rq.get_cookie(url, cookie_file_name="wx")
htmlStr = u'%s' % htmlStr
except Exception, ex:
print ex
return
comment_id = None
if re_comment_id:
comment_id = re_comment_id.groups()[0]
print u"文章ID=%s,biz=%s,留言板ID=%s" % (mid, biz, comment_id)
if comment_id is None:
print u'comment_id不存在'
return
# 请求留言接口
api_url = 'http://mp.weixin.qq.com/mp/appmsg_comment?action=getcomment&__biz=%s&appmsgid=%s&idx=1&comment_id=%s&offset=0&limit=100' % (
biz, mid, comment_id)
commonDataStr = None
try:
commonDataStr = rq.get_cookie(
api_url,
cookie_file_name="wx",
headers={
"User-agent":
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1"
})
except Exception, ex:
print ex
return
# 解析留言数据为JSON格式
if commonDataStr.find(u'请在微信客户端打开链接') > -1:
print u'请在微信客户端打开链接'
return
commonDataJson = json.loads(commonDataStr)
return commonDataJson