def get_blog_by_page(self, containerid, page, name):
blog_list = []
if page > 50:
print("页数不能大于50")
return False
try:
for i in range(page):
url = 'https://m.weibo.cn/api/container/getIndex?containerid=%s&page=%s' % (containerid, i)
res = requests.get(url, headers=self.headers).json()
cards = res['data']['cards']
try:
for j in range(len(cards)):
print("-----正在爬取第" + str(i) + "页，第" + str(j + 1) + "条微博------")
blog_dict = get_blog_info(cards, j, name, i)
blog_list.append(blog_dict)
except:
raise
return blog_list
except:
raise
def get_blog_by_text(self, containerid, blog_text, name):
print('containerid: ', containerid)
blog_list = []
page = 1
while True:
try:
url = 'https://m.weibo.cn/api/container/getIndex?containerid=%s&page=%s' % (containerid, page)
res_code = requests.get(url).status_code
if res_code == 418:
print("访问太频繁，过会再试试吧")
return False
res = requests.get(url).json()
cards = res['data']['cards']
print('page', page)
print('cards: ', cards)
if len(cards) > 0:
for i in range(len(cards)):
print("-----正在爬取第" + str(page) + "页，第" + str(i+1) + "条微博------")
blog_dict = get_blog_info(cards, i, name, page)
if blog_dict is False:
continue
blog_list.append(blog_dict)
mblog_text = blog_dict['mblog_text']
create_time = blog_dict['create_time']
if blog_text in mblog_text:
print("成功找到相关微博")
return blog_dict['mblog_id']
elif checkTime(create_time, config.day) is False:
print("在配置的时间内没有找到相关微博")
return blog_list
time.sleep(config.sleep_time)
page += 1
time.sleep(config.sleep_time)
else:
print("没有任何微博哦！")
break
except:
pass
def get_blog_by_text(self, containerid, blog_text, name):
blog_list = []
page = 1
while True:
try:
url = 'https://m.weibo.cn/api/container/getIndex?containerid=%s&page=%s' % (containerid, page)
res_code = requests.get(url).status_code
if res_code == 418:
print("访问太频繁，过会再试试吧")
return False
res = requests.get(url).json()
cards = res['data']['cards']
if len(cards) > 0:
for i in range(len(cards)):
print("-----正在爬取第" + str(page) + "页，第" + str(i+1) + "条微博------")
blog_dict = get_blog_info(cards, i, name, page)
blog_list.append(blog_dict)
if blog_list is False:
break
mblog_text = blog_dict['mblog_text']
create_time = blog_dict['create_time']
if blog_text in mblog_text:
print("找到相关微博")
return blog_dict['mblog_id']
elif checkTime(create_time) is False:
print("没有找到相关微博")
return blog_list
# if cards[i]['card_type'] == 9:
# scheme = cards[i]['scheme'] # 微博地址
# mblog = cards[i]['mblog']
# mblog_text = mblog['text']
# create_time = mblog['created_at']
# mblog_id = mblog['id']
# reposts_count = mblog['reposts_count'] # 转发数量
# comments_count = mblog['comments_count'] # 评论数量
# attitudes_count = mblog['attitudes_count'] # 点赞数量
# with open(name, 'a', encoding='utf-8') as f:
# f.write("----第"+str(page)+"页，第"+str(i+1)+"条微博----"+"\n")
# f.write("微博地址：" + str(scheme) + "\n" + "发布时间：" + str(create_time) + "\n"
# + "微博内容：" + mblog_text + "\n" + "点赞数：" + str(attitudes_count) + "\n"
# + "评论数：" + str(comments_count) + "\n" + "转发数：" + str(reposts_count) + "\n")
# blog_dict['mblog_id'] = mblog_id
# blog_dict['mblog_text'] = mblog_text
# blog_dict['create_time'] = create_time
# blog_list.append(blog_dict)
# if blog_text in mblog_text:
# print("找到相关微博")
# return blog_list
# elif checkTime(create_time) is False:
# print("没有找到相关微博")
# return blog_list
# else:
# print("没有任何微博哦")
# break
page += 1
time.sleep(config.sleep_time)
else:
print("没有任何微博哦")
break
except:
pass