def init():
for i in range(20):
ascp = public.get_ASCP()
form = {
'ac': 'wap',
'format': 'json_raw',
'min_behot_time': int(time.time()),
'as': ascp[0],
'enable_stick': 'false',
'tag': 'video',
'cp': ascp[1],
}
for item in public.request_data(LIST_API,
cookie=COOKIE,
header=HEADER,
params=form).get('data', []):
video = {}
video['_id'] = public.format_id(item.get('title'))
video['title'] = item.get('title')
video['from'] = '今日头条'
video['pic'] = item.get('large_image_url')
r, s = public.get_rs(item.get('video_id'))
video['url'] = base64.b64decode(
public.request_data(
DETAIL_API + item.get('video_id'),
params={
'r': r,
's': s
},
header=HEADER).get('data').get('video_list').
get('video_1').get('main_url').encode('utf-8')).decode('utf-8')
video['timestamp'] = int(time.time())
public.save_data(video, DB_NAME)
def scrapy_list(type_info):
ascp = public.get_ASCP()
form = {
'ac': 'wap',
'format': 'json_raw',
'min_behot_time': int(time.time()),
'as': ascp[0],
'enable_stick': 'false',
'tag': type_info.get('tag'),
'cp': ascp[1],
}
for item in public.request_data(LIST_API,
cookie=COOKIE,
header=HEADER,
params=form).get('data', []):
save_data = {
'_id':
public.format_id(item.get('title')),
'title':
item.get('title'),
'imageurls':
list(map(lambda x: x.get('url'), item.get('image_list')))[:3],
'tag':
type_info.get('name'),
'timestamp':
int(time.time()),
'from':
'今日头条',
'detail':
scrapy_detail(item.get('source_url'))
}
if save_data.get('detail'):
public.save_data(save_data, DB_NAME)
def scrapy_detail(id):
try:
data = json.loads(
public.request_data(DETAIL_API + '?id=' + id,
header=HEADER).get('data').get('content', []))
detail = []
for item in data:
content = {}
if item.get('type') == 'cnt_article':
content['type'] = 'text'
content['data'] = item.get('desc')
elif item.get('type') == 'img_url':
content['type'] = 'image'
if item.get('img'):
content['data'] = item.get('img').get('imgurl1000').get(
'imgurl')
if not content['data']:
content['data'] = item.get('img').get('imgurl640').get(
'imgurl')
if not content['data']:
content['data'] = item.get('img').get('imgurl0').get(
'imgurl')
elif item.get('img_url'):
content['data'] = item.get('img_url')
detail.append(content)
return detail
except Exception as e:
print(e, id)
def scrapy_list(cookie, category__name, timesample):
list_postdata = {
'from': 'news_webapp',
'pd': 'webapp',
'os': 'android',
'mid': cookie['BAIDUID'],
'ver': 6,
'category_name': category__name,
'action': 0,
'display_time': timesample,
'wf': 0,
}
data = public.request_data(LISTAPI, params=list_postdata,
cookie=cookie).get('data').get('news', [])
for item in data:
save_data = {
'_id':
public.format_id(item.get('title')),
'title':
item.get('title'),
'imageurls':
list(
map(lambda x: x.get('url_webp', ''), item.get('imageurls',
[]))),
'tag':
category__name,
'timestamp':
int(time.time()),
'from':
'百度新闻',
'detail':
scrapy_detail(item.get('nid'), category__name)
}
if save_data.get('detail') and len(save_data.get('detail')) > 1:
public.save_data(save_data, DB_NAME)
def scrapy_list(nextUrl, type_info):
if nextUrl:
data = public.request_data(nextUrl)
else:
data = public.request_data(LIST_API + type_info['tag'])
for item in data.get('contList', []):
save_data = {
'_id': public.format_id(item.get('name')),
'title': item.get('name'),
'imageurls': [item.get('pic')],
'tag': type_info['name'],
'timestamp': int(time.time()),
'from': '澎湃新闻',
'detail': scrapy_detail(item['contId'])
}
if save_data.get('detail'):
public.save_data(save_data, DB_NAME)
return data.get('nextUrl')
def init():
for channel in CHANNELS:
for i in range(20):
for item in public.request_data(LIST_API,
params={
'channel': channel,
'page': i
}).get('videos', []):
video = {}
video['_id'] = public.format_id(item.get('title'))
video['title'] = item.get('title')
video['from'] = '百度视频'
video['pic'] = item.get('imgh_url')
video['url'] = public.request_data(
DETAIL_API,
params={
'id': item.get('url').split('/')[-1].split('.')[0]
}).get('data').get('main_video').get('source').get('mp4')
video['timestamp'] = int(time.time())
public.save_data(video, DB_NAME)
def init():
for i in range(20):
form = {
'cateid': 'uM',
'mod': 'mpvideo',
'action': 1,
'up': i,
'down': 0,
'did': '41ea3bde383860b6',
'imei': '',
'length': 13,
'net_type': 2,
'ad': {
"originfrom": "huawei-q",
"imei": "868384032192527",
"channel": "news_ent",
"osVersion": "9",
"deviceModel": "HWI-AL00",
"platform": "android",
"from": "fastapp"
},
'app_type': 124,
'cre': 'tianyi',
'merge': 3,
'statics': 1,
'ldid': '',
'uid': ''
}
for item in public.request_data(LIST_API, params=form).get('data', []):
video = {}
video['_id'] = public.format_id(item.get('title'))
video['title'] = item.get('title')
video['from'] = '新浪视频'
video['pic'] = item.get('thumb')
video['url'] = public.request_data(
DETAIL_API, params={
'docUrl': item.get('surl')
}).get('data').get('videosModule')[0].get('data')[0].get(
'videoInfo').get('url')
video['timestamp'] = int(time.time())
public.save_data(video, DB_NAME)
def init():
for lc in range(20):
for item in public.request_data(API + str(lc)).get('data').get(
'videoList', []):
video = {}
video['_id'] = public.format_id(item.get('title'))
video['title'] = item.get('title')
video['from'] = '搜狐视频'
video['pic'] = item.get('tvPic')
video['url'] = item.get('playUrl')
video['timestamp'] = int(time.time())
public.save_data(video, DB_NAME)
def init():
for i in range(20):
form = {'rtype': 0, 'pageNum': i, 'pageSize': 10}
for item in public.request_data(LIST_API,
params=form,
header=HEADER,
method='POST').get('page').get(
'result', []):
video = {}
video['_id'] = public.format_id(item.get('title'))
video['title'] = item.get('title')
video['from'] = '看鉴视频'
video['pic'] = item.get('image')
video['url'] = public.request_data(
DETAIL_API,
params={
'videoId': item['rid']
},
header=HEADER,
method='POST').get('upyunVideos')[0].get('playurl')
video['timestamp'] = int(time.time())
public.save_data(video, DB_NAME)
def init():
for channel_id in CHANNEL_IDS:
for i in range(20):
form = {
'app': 'howto_a',
'udid': '41ea3bde383860b6',
'channel_id': channel_id,
'timestamp': int(time.time())
}
for item in public.request_data(LIST_API,
params=form).get('contents', []):
video = {}
video['_id'] = public.format_id(item.get('video').get('name'))
video['title'] = item.get('video').get('name')
video['from'] = '好兔视频'
video['pic'] = item.get('video').get('share_img')
video['url'] = public.request_data(
DETAIL_API, params={
'id': item.get('id')
}).get('bitrates')[-1].get('uri')
video['timestamp'] = int(time.time())
public.save_data(video, DB_NAME)
def init():
global API
for i in range(20):
res = public.request_data(API)
for item in res.get('contList', []):
video = {}
video['_id'] = public.format_id(item.get('name'))
video['title'] = item.get('name')
video['from'] = '梨视频'
video['pic'] = item.get('pic')
video['url'] = item.get('videos')[0].get('url')
video['timestamp'] = int(time.time())
API = res.get('nextUrl')
public.save_data(video, DB_NAME)
def scrapy_detail(nid, tag):
try:
detail_postdata = {
'cuid': '',
'nids': nid,
'wf': 1,
'remote_device_type': 1,
'os_type': 1,
'screen_size_width': 1080,
'screen_size_height': 1920,
}
data = public.request_data(
DETAILAPI, params=detail_postdata).get('data').get('news')[0]
return list(map(format_detail, data.get('content')))
except Exception as e:
print(e, 1)
def scrapy_list(type_info, count):
form = {'channel': type_info.get('tag'), 'page': count}
data = public.request_data(LIST_API, params=form,
header=HEADER).get('data', [])
if data:
for item in data:
save_data = {
'_id': public.format_id(item.get('title')),
'title': item.get('title'),
'imageurls': item.get('img_urls'),
'tag': type_info.get('name'),
'timestamp': int(time.time()),
'from': '腾讯新闻',
'detail': scrapy_detail(item.get('id'))
}
if save_data.get('detail'):
public.save_data(save_data, DB_NAME)
def init():
global LIST_API
for i in range(20):
res = public.request_data(LIST_API, params=FORM)
for item in res.get('contList', []):
video = {}
video['_id'] = public.format_id(item.get('name'))
video['title'] = item.get('name')
video['from'] = '澎湃视频'
video['pic'] = item.get('pic')
video['url'] = etree.HTML(
public.request_html(DETAIL_API,
params={
'contid': item['contId']
})).xpath("//*[@class='m']/@href")[0]
video['timestamp'] = int(time.time())
LIST_API = res.get('nextUrl')
public.save_data(video, DB_NAME)
def scrapy_detail(aid):
try:
form = {
'st': '',
'df': 'androidphone',
'loginid': '',
'os': 'android',
'city': '',
'screen': '1080x1794',
'nw': 'wifi',
'deviceid': '',
'publishid': '5286',
'gv': '5.7.2',
'uid': '868384032192527',
'province': '',
'av': '5.7.2',
'proid': 'ifengnews',
'district': '',
'limit': 5,
'from': 'xiaomi',
'sn': '',
'aid': aid,
'vt': 5,
}
res = public.request_data(DETAIL_API,
params=form).get('body').get('text')
data = etree.HTML(res)
detail = []
for item in data.xpath('//*'):
if item.xpath('text()'):
content = {}
content['type'] = 'text'
content['data'] = item.xpath('text()')[0]
detail.append(content)
if item.xpath('img/@src'):
content = {}
content['type'] = 'image'
content['data'] = item.xpath('img/@src')[0]
detail.append(content)
return detail
except Exception as e:
print(e)
def scrapy_list(type_info, count):
form = {
'cateid': type_info['cateid'],
'mod': type_info['mod'],
'action': 2,
'up': count,
'down': 0,
'did': '41ea3bde383860b6',
'imei': '',
'length': 13,
'net_type': 2,
'ad': {
"originfrom": "huawei-q",
"imei": "868384032192527",
"channel": "news_ent",
"osVersion": "9",
"deviceModel": "HWI-AL00",
"platform": "android",
"from": "fastapp"
},
'app_type': 124,
'cre': 'tianyi',
'merge': 3,
'statics': 1,
'ldid': '',
'uid': ''
}
for item in public.request_data(LIST_API, params=form).get('data', []):
if item.get('thumbs'):
save_data = {
'_id': public.format_id(item.get('title')),
'title': item.get('title'),
'imageurls': item.get('thumbs')[:3],
'tag': type_info.get('category__name'),
'timestamp': int(time.time()),
'from': '新浪新闻',
'detail': scrapy_detail(item.get('url'))
}
if save_data.get('detail'):
public.save_data(save_data, DB_NAME)
def scrapy_list(type_info, count):
form = {
'st': '',
'df': '',
'pullNum': count,
'loginid': '',
'os': 'android',
'city': '',
'screen': '',
'nw': '',
'deviceid': '',
'gv': '5.7.3',
'publishid': '',
'uid': '868384032192527',
'lastDoc': '',
'province': '',
'av': 0,
'district': '',
'proid': 'ifengnews',
'action': 'default',
'id': type_info.get('tag'),
'sn': '',
'vt': 5,
}
data = public.request_data(LIST_API, params=form)[0]
if data:
for item in data.get('item'):
if item.get('thumbnail') and item.get('id'):
save_data = {
'_id': public.format_id(item.get('title')),
'title': item.get('title'),
'imageurls': [item.get('thumbnail')],
'tag': type_info.get('name'),
'timestamp': int(time.time()),
'from': '凤凰新闻',
'detail': scrapy_detail(item.get('id'))
}
if save_data.get('detail'):
public.save_data(save_data, DB_NAME)
def scrapy_detail(source_url):
try:
res = public.request_data(DETAIL_API + source_url + 'info/',
cookie=COOKIE,
header=HEADER).get('data').get('content')
data = etree.HTML(res)
detail = []
for item in data.xpath('//*/div[1]/*'):
if item.xpath('text()'):
content = {}
content['type'] = 'text'
content['data'] = item.xpath('text()')[0]
detail.append(content)
if item.xpath('img/@src'):
content = {}
content['type'] = 'image'
content['data'] = item.xpath('img/@src')[0]
detail.append(content)
return detail
except Exception as e:
print(e)
def scrapy_detail(doc_url):
try:
data = public.request_data(DETAIL_API + doc_url).get('data')
if data.get('pics'):
pics = list(
map(lambda x: x.get('data').get('pic'), data.get('pics')))
text = re.split(r'<!--{IMG_\d}-->',
data.get('content').replace('<br/>', ''))
i = 0
content = []
for item in text:
content.append({'type': 'text', 'data': item})
if i >= 1 and i <= len(text) - 2:
content.append({'type': 'image', 'data': pics[i]})
i += 1
return content
elif data.get('picsModule'):
content = []
for item in data.get('picsModule')[0].get('data'):
content.append({'type': 'text', 'data': item.get('alt')})
content.append({'type': 'image', 'data': item.get('pic')})
return content
except Exception as e:
print(e)
