def test_replace_html(self):
html = ''''"&¥amp;<> \\'''
assert_equal(replace_html(html), '\'"&¥<> ')
html = [''', '"', '&', '¥', 'amp;', '<', '>', ' ', '\\']
assert_equal(replace_html(html), ['\'', '"', '&', '¥', '', '<', '>', ' ', ''])
html = {''': '"'}
assert_equal(replace_html(html), {'\'': '"'})
def test_replace_html(self):
html = ''''"&¥amp;<> \\'''
assert_equal(replace_html(html), '\'"&¥<> ')
html = [''', '"', '&', '¥', 'amp;', '<', '>', ' ', '\\']
assert_equal(replace_html(html), ['\'', '"', '&', '¥', '', '<', '>', ' ', ''])
html = {''': '"'}
assert_equal(replace_html(html), {'\'': '"'})
def __handle_content_url(content_url):
content_url = replace_html(content_url)
return ('http://mp.weixin.qq.com{}'.format(content_url)
if 'http://mp.weixin.qq.com' not in content_url else
content_url) if content_url else ''
def get_article_by_history_json(text, article_json=None, **kwargs):
"""从 历史消息页的文本 提取文章列表信息
Parameters
----------
text : str or unicode
历史消息页的文本
article_json : dict
历史消息页的文本 提取出来的文章json dict
kwargs
??
Returns
-------
list of dict
{
??
}
"""
# TODO 加上返回的数据的文档
if article_json is None:
article_json = find_article_json_re.findall(text)
article_json = article_json[0] + '}}]}'
article_json = json.loads(article_json)
biz = kwargs.get('biz', '')
uin = kwargs.get('uin', '')
key = kwargs.get('key', '')
items = list()
for listdic in article_json['list']:
item = dict()
comm_msg_info = listdic['comm_msg_info']
item['send_id'] = comm_msg_info.get('id',
'') # 不可判重，一次群发的消息的id是一样的
item['datetime'] = comm_msg_info.get('datetime', '')
item['type'] = str(comm_msg_info.get('type', ''))
if item['type'] == '1':
# 文字
item['content'] = comm_msg_info.get('content', '')
elif item['type'] == '3':
# 图片
item[
'img_url'] = 'https://mp.weixin.qq.com/mp/getmediadata?__biz=' + biz + '&type=img&mode=small&msgid=' + \
str(item['qunfa_id']) + '&uin=' + uin + '&key=' + key
elif item['type'] == '34':
# 音频
item['play_length'] = listdic['voice_msg_ext_info'].get(
'play_length', '')
item['fileid'] = listdic['voice_msg_ext_info'].get(
'fileid', '')
item['audio_src'] = 'https://mp.weixin.qq.com/mp/getmediadata?__biz=' + biz + '&type=voice&msgid=' + \
str(item['qunfa_id']) + '&uin=' + uin + '&key=' + key
elif item['type'] == '49':
# 图文
app_msg_ext_info = listdic['app_msg_ext_info']
url = app_msg_ext_info.get('content_url')
url = replace_html(url)
if url:
url = 'http://mp.weixin.qq.com' + url if 'http://mp.weixin.qq.com' not in url else url
else:
url = ''
item['main'] = 1
item['title'] = app_msg_ext_info.get('title', '')
item['digest'] = app_msg_ext_info.get('digest', '')
item['fileid'] = app_msg_ext_info.get('fileid', '')
item['content_url'] = url
item['source_url'] = app_msg_ext_info.get('source_url', '')
item['cover'] = app_msg_ext_info.get('cover', '')
item['author'] = app_msg_ext_info.get('author', '')
item['copyright_stat'] = app_msg_ext_info.get(
'copyright_stat', '')
items.append(item)
if app_msg_ext_info.get('is_multi', 0) == 1:
for multidic in app_msg_ext_info[
'multi_app_msg_item_list']:
url = multidic.get('content_url')
if url:
url = 'http://mp.weixin.qq.com' + url if 'http://mp.weixin.qq.com' not in url else url
else:
url = ''
itemnew = dict()
itemnew['send_id'] = item[
'send_id'] # TODO send_id 和 qunfa_id 只有一个可以通过测试
itemnew['datetime'] = item['datetime']
itemnew['type'] = item['type']
itemnew['main'] = 0
itemnew['title'] = multidic.get('title', '')
itemnew['digest'] = multidic.get('digest', '')
itemnew['fileid'] = multidic.get('fileid', '')
itemnew['content_url'] = url.replace('&', '&')
itemnew['source_url'] = multidic.get('source_url', '')
itemnew['cover'] = multidic.get('cover', '')
itemnew['author'] = multidic.get('author', '')
itemnew['copyright_stat'] = multidic.get(
'copyright_stat', '')
items.append(itemnew)
continue
elif item['type'] == '62':
item['cdn_videoid'] = listdic['video_msg_ext_info'].get(
'cdn_videoid', '')
item['thumb'] = listdic['video_msg_ext_info'].get('thumb', '')
item[
'video_src'] = 'https://mp.weixin.qq.com/mp/getcdnvideourl?__biz=' + biz + '&cdn_videoid=' + item[
'cdn_videoid'] + '&thumb=' + item[
'thumb'] + '&uin=' + uin + '&key=' + key
items.append(item)
items_new = [] # 删除搜狗本身携带的空数据
for item in items:
if (int(item['type']) == 49) and (not item['content_url']):
pass
else:
items_new.append(item)
return items_new
def __handle_content_url(content_url):
content_url = replace_html(content_url)
return ('http://mp.weixin.qq.com{}'.format(
content_url) if 'http://mp.weixin.qq.com' not in content_url else content_url) if content_url else ''