def content_handle(movie):
# movie_names = re.findall(rer1, movie, re.S)
# print(movie_names)
_id = list(
set(re.findall('https://movie.douban.com/subject/(\\d*?)/', movie)))
if len(_id) == 1:
_id = _id[0]
else:
print(_id)
raise Exception("!!!more than one!")
comment_table_create(_id)
db = DbHandle(database='comment')
db.table = _id
block = re.findall('id="comments".*?id="paginator"', movie, re.S)
block = block[0]
# soup = BeautifulSoup(movie, 'lxml')
# comments = soup.find_all(class_='comment-item')
pattern = 'title="(.*?)".*?"https://www.douban.com/people/(.*?)/".*?src="(.*?)".*?<.*?comment-time.*?title="(.*?)".*?short">(.*?)<'
comments = re.findall(pattern, block, re.S)
# x = 1
for comment in comments[:10]:
pic = re.sub('/u(.*?)-.*?\\.', '/ul\\1.', comment[2])
data = [
comment[1], comment[0],
str(comment[3]).replace('\n', ''), '''{}'''.format(comment[4])
]
print(_id, comment[1], pic, comment[2],
str(comment[3]).replace('\n', ''), '''{}'''.format(comment[4]))
db.save(data)
def db_save(name, data):
db = DbHandle()
db.table = 'init'
data_ = [name, data]
try:
db.save(data_)
except Exception as e:
print(e)
def content_handle(movie_id, content):
block = re.findall('type="application/ld\\+json".*?datePublished', content, re.S)
# print(block)
actors = re.findall('celebrity/(\\d*?)/', block[0])
db = DbHandle()
db.table = 'movie_cast'
for actor in actors:
try:
if not db.get(_filter='where person_id={} and movie_id={}'.format(actor, movie_id)):
print(actor)
db.save(data=[movie_id, actor], _range='movie_id, person_id')
else:
print(movie_id, actor, 'Already have this connect')
except Exception as e:
# 桐本拓哉，你狠
if actor == '1376098':
db.save(data=[movie_id, '1250852'], _range='movie_id, person_id')
continue
db.close()
print(e)
extra(actor)
print(actor)
db = DbHandle()
db.table = 'movie_cast'
db.save(data=[movie_id, actor], _range='movie_id, person_id')
def content_handle(info):
# all_actor_information = []
_id = re.findall(
'id="headline".*?rel="nofollow".*?https://movie.douban.com/celebrity/(\d*?)/',
info, re.S)
data = [_id[0]]
name = re.findall(r'<div id="content">.*?<h1>(.+)</h1>', info, re.S)[0]
try:
sex = re.findall(r'<span>性别<.+>:\s*(.*)\s*', info)[0]
except:
print('Can not find actor sex')
sex = None
try:
constellation = re.findall(r'<span>星座<.+>:\s*(.*)\s*', info)[0]
except:
print('Can not find constellation')
constellation = None
try:
birthday = re.findall(r'<span>出生日期<.+>:\s*(.*)\s*', info)[0]
except Exception as e:
try:
birthday = re.findall(r'<span>生卒日期<.+>:\s*(.*)\s*', info)[0]
except:
print('Can not find birthday')
birthday = None
try:
birthplace = re.findall(r'<span>出生地<.+>:\s*(.*)\s*', info)[0]
except:
print('Can not find birthplace')
birthplace = None
try:
profession = re.findall(r'<span>职业<.+>:\s*(.*)\s*', info)[0]
except:
print('Can not find profession')
profession = None
try:
imdb_number = re.findall(r'<span>imdb编号<.+>:\s*.+>(.+)</a>', info)[0]
except:
print('Can not find IMDB编号')
imdb_number = None
all_introduce = re.findall(r'<span class="all hidden">\s*(.+)<', info)
if not bool(all_introduce):
normal_introduce = re.findall(
r'<h2>\s*影人简介\s*.+\s*<.+>\s*</div>\s*<div class="bd">\s*(.+)\s*',
info)
_dict = {
"姓名": name,
"性别": sex,
"星座": constellation,
"出生日期": birthday,
"出生地": birthplace,
"职业": profession,
"imdb编号": imdb_number,
"简介": normal_introduce[0]
}
# all_actor_information.append(dict)
else:
_dict = {
"姓名": name,
"性别": sex,
"星座": constellation,
"出生日期": birthday,
"出生地": birthplace,
"职业": profession,
"imdb编号": imdb_number,
"简介": all_introduce[0]
}
# all_actor_information.append(dict)
# print(_dict)
data.extend(_dict.values())
if data[-1] == '</div>':
data[-1] = None
db = DbHandle()
db.table = 'movie_person'
if not db.get_by_id(_id=int(_id[0])):
print(data)
db.save(data)
else:
print('Already have this')