def sendPhoto(url, item):
result = Result()
src = findSrc(item)
if not src:
return
result.imgs = [src]
result.cap = item.find('span', itemprop='caption').text
album_sender.send(channel, url, result)
def getAlbum(url,
force_cache=True,
word_limit=200,
paragraph_limit=3,
append_source=False,
append_url=True):
content = _getArticle(url, force_cache=force_cache).text
album = AlbumResult()
for item in content.findAll('img'):
path = item.get('src')
if not path:
continue
try:
cached_url.get(path, mode='b', force_cache=True)
img = Image.open(cached_url.getFilePath(path))
except:
continue
w, h = img.size
file_size = os.stat(cached_url.getFilePath(path)).st_size
if 36000 < file_size < 36200 and w == 1080 and h == 1080: # 界面文化题头
continue
if 27000 < file_size < 27300 and w == 640 and h == 640: # 思想市场
continue
if w == 750 and h == 234: # 界面文化题头
continue
if 6000 < file_size < 9000 and w == 347 and h == 347: # 界面文化题头
continue
if 87000 < file_size < 91000 and w == 900 and h == 500: # 美国华人杂谈题头
continue
if 53000 < file_size < 56000 and w == 795 and h == 504: # 微信foot
continue
if 57000 < file_size < 61000 and w == 1011 and h == 282: # 短史记题头
continue
if w * 0.25 < h < w * 4 and min(w, h) > 100 and max(w, h) > 300:
# print(file_size, w, h)
album.imgs.append(item.get('src'))
break
for tag in ['img', 'br']:
for item in content.findAll(tag):
item.replace_with('\n\n')
for item in content.findAll('p'):
item.append('\n\n')
title = '【%s】\n\n' % getTitle(url)
lines = content.text.split('\n')
lines = [line.strip() for line in lines]
lines = [line for line in lines if isGoodLine(line)]
if paragraph_limit < 5:
lines = [line for line in lines if not line or len(line) > 20]
lines = cutCaptionHtml('\n'.join(lines),
word_limit).strip().strip('\ufeff').strip()
lines = lines.split('\n')
lines = lines[:paragraph_limit * 2]
album.cap_html_v2 = title + '\n'.join(lines).strip()
if append_url:
album.cap_html_v2 += '\n\n' + url
if append_source:
album.url = url
return album
def get(url):
r = Result()
r.url = url
content = cached_url.get(url, force_cache=True)
soup = BeautifulSoup(content, 'html.parser')
r.title = soup.find('meta', {'property': 'og:title'})['content']
r.cap_html = r.title
r.imgs = list(getImages(content))
return r
def get(path, force_cache=False, content=None):
path = path.replace('m.douban.com', 'www.douban.com')
content = content or getContent(path, force_cache=force_cache)
b = BeautifulSoup(str(content), features='html.parser')
result = Result()
result.imgs = getImgs(b, path)
result.cap = getCap(b, path)
result.video = getVideo(b)
result.url = path
return result
def get(path):
parts = path.split('/')
channel = parts[3]
post_id = int(parts[4])
post = webgram.getPost(channel, post_id)
result = Result()
result.url = path
result.cap_html = getCap(post)
result.imgs = getImgs(post)
result.video = post.getVideo()
return result
def cut(update, context):
msg = update.effective_message
if msg.chat_id == debug_group.id or msg.media_group_id:
return
file = msg.document or (msg.photo and msg.photo[-1])
file_path = (file and file.get_file().file_path) or msg.text or ''
if not file_path.startswith('http'):
return
result = AlbumResult()
result.cap = msg.caption_markdown or msg.text_markdown or ''
result.imgs = [file_path]
album_sender.send_v2(msg.chat, result, send_all=True, size_factor=2.1)
def get(path, json=None):
wid = getWid(path)
r = Result()
if not json:
try:
json = yaml.load(cached_url.get(prefix + wid),
Loader=yaml.FullLoader)
json = json['data']
except:
return r
if 'test' in sys.argv:
with open('tmp/%s.json' % wid, 'w') as f:
f.write(str(json))
r.imgs = getImages(json) or getImages(json.get('retweeted_status', {}))
r.cap_html = json['text']
r.title = json.get('status_title')
r.cap_html_v2 = getCap(json)
r.video = getVideo(json) or getVideo(json.get('retweeted_status', {}))
r.wid = json.get('id')
r.rwid = json.get('retweeted_status', {}).get('id', '')
r.hash = getHash(json)
r.url = path
return r
def testPicBot():
result = Result()
result.cap_html = 'test'
print(result)
r = album_sender.send_v2(chat, result, send_all=True, time_sleep=5)
print(r)