// 安裝requests依賴
pip install requests

// 安裝lxml依賴
pip install lxml

// 安裝pymysql依賴
pip install pymysql

#!/user/bin env python
# 獲取電影天堂詳細(xì)信息
import requests
import time
from lxml import etree
import pymysql
requests.adapters.DEFAULT_RETRIES = 5
# 偽裝瀏覽器
HEADERS ={
	'User-Agent':'Mozilla/5.(Windows NT 10.0; WOW64) AppleWebKit/537.3(KHTML, like Gecko) Chrome/63.0.3239.13Safari/537.36',
    'Host':'www.dy2018.com'
}
# 定義全局變量
BASE_DOMAIN = 'https://www.dy2018.com/'
# 獲取首頁(yè)網(wǎng)頁(yè)信息并解析
def getUrlText(url,coding):
	s = requests.session()
	#print("獲取首頁(yè)網(wǎng)頁(yè)信息并解析：", url)
	respons = s.get(url,headers=HEADERS)
	print("請(qǐng)求URL：", url)
	if(coding=='c'):
		urlText = respons.content.decode('gbk')
		html = etree.HTML(urlText)  # 使用lxml解析網(wǎng)頁(yè)
	else:
		urlText = respons.text
		html = etree.HTML(urlText)  # 使用lxml解析網(wǎng)頁(yè)
	s.keep_alive = False
	return html

# 獲取電影詳情頁(yè)的href,text解析
def getHref(url):
	html = getUrlText(url,'t')
	aHref = html.xpath('//table[@class="tbspan"]//a/@href')
	print("獲取電影詳情頁(yè)的href,text解析```")
	htmlAll = map(lambda url:BASE_DOMAIN+url,aHref) # 給每個(gè)href補(bǔ)充BASE_DOMAIN
	return htmlAll

# 使用content解析電影詳情頁(yè)，并獲取詳細(xì)信息數(shù)據(jù)
def getPage(url):
	html = getUrlText(url,'c')
	moveInfo = {}  # 定義電影信息
	mName = html.xpath('//div[@class="title_all"]//h1/text()')[0]
	moveInfo['movie_name'] = mName
	mDiv = html.xpath('//div[@id="Zoom"]')[0]
	mImgSrc = mDiv.xpath('.//img/@src')
	moveInfo['image_path'] = mImgSrc[0]  # 獲取海報(bào)src地址
	if len(mImgSrc) >= 2:
		moveInfo['screenshot'] = mImgSrc[1]  # 獲取電影截圖src地址
	mContnent = mDiv.xpath('.//text()')
	def pares_info(info,rule):
		'''
		:param info: 字符串
		:param rule: 替換字串
		:return:  指定字符串替換為空，并剔除左右空格
		'''
		return info.replace(rule,'').strip()
	for index,t in enumerate(mContnent):
		if t.startswith('◎譯　　名'):
			name = pares_info(t,'◎譯　　名')
			moveInfo['translation']=name
		elif t.startswith('◎片　　名'):
			name = pares_info(t,'◎片　　名')
			moveInfo['movie_title']=name
		elif t.startswith('◎年　　代'):
			name = pares_info(t,'◎年　　代')
			moveInfo['movie_age']=name
		elif t.startswith('◎產(chǎn)　　地'):
			name = pares_info(t,'◎產(chǎn)　　地')
			moveInfo['movie_place']=name
		elif t.startswith('◎類　　別'):
			name = pares_info(t,'◎類　　別')
			moveInfo['category']=name
		elif t.startswith('◎語(yǔ)　　言'):
			name = pares_info(t,'◎語(yǔ)　　言')
			moveInfo['language']=name
		elif t.startswith('◎字　　幕'):
			name = pares_info(t,'◎字　　幕')
			moveInfo['subtitle']=name
		elif t.startswith('◎上映日期'):
			name = pares_info(t,'◎上映日期')
			moveInfo['release_date']=name
		elif t.startswith('◎豆瓣評(píng)分'):
			name = pares_info(t,'◎豆瓣評(píng)分')
			moveInfo['douban_score']=name
		elif t.startswith('◎片　　長(zhǎng)'):
			name = pares_info(t,'◎片　　長(zhǎng)')
			moveInfo['file_length']=name
		elif t.startswith('◎?qū)А　⊙?):
			name = pares_info(t,'◎?qū)А　⊙?)
			moveInfo['director']=name
		elif t.startswith('◎編　　劇'):
			name = pares_info(t, '◎編　　劇')
			writers = [name]
			for i in range(index + 1, len(mContnent)):
				writer = mContnent[i].strip()
				if writer.startswith('◎'):
					break
				writers.append(writer)
			moveInfo['screenwriter'] = writers
		elif t.startswith('◎主　　演'):
			name = pares_info(t, '◎主　　演')
			actors = [name]
			for i in range(index+1,len(mContnent)):
				actor = mContnent[i].strip()
				if actor.startswith('◎'):
					break
				actors.append(actor)
			moveInfo['stars'] = " ".join(actors)
		elif t.startswith('◎標(biāo)　　簽'):
			name = pares_info(t,'◎標(biāo)　　簽')
			moveInfo['tags']=name
		elif t.startswith('◎簡(jiǎn)　　介'):
			name = pares_info(t,'◎簡(jiǎn)　　介')
			profiles = []
			for i in range(index + 1, len(mContnent)):
				profile = mContnent[i].strip()
				if profile.startswith('◎獲獎(jiǎng)情況') or '【下載地址】' in profile:
					break
				profiles.append(profile)
			moveInfo['introduction']=" ".join(profiles)
		elif t.startswith('◎獲獎(jiǎng)情況'):
			name = pares_info(t,'◎獲獎(jiǎng)情況')
			awards = []
			for i in range(index + 1, len(mContnent)):
				award = mContnent[i].strip()
				if '【下載地址】' in award:
					break
				awards.append(award)
			moveInfo['awards']=" ".join(awards)
	moveInfo['movie_url'] = url
	return moveInfo

# 獲取前n頁(yè)所有電影的詳情頁(yè)href
def spider():
	#連接數(shù)據(jù)庫(kù)
	base_url = 'https://www.dy2018.com/html/gndy/dyzz/index_{}.html'
	moves = []
	m = int(input('請(qǐng)輸入您要獲取的開(kāi)始頁(yè)：'))
	n = int(input('請(qǐng)輸入您要獲取的結(jié)束頁(yè)：'))
	print('即將寫入第{}頁(yè)到第{}頁(yè)的電影信息，請(qǐng)稍后...'.format(m, n))
	for i in range(m,n+1):
		print('******* 第{}頁(yè)電影 正在寫入 ********'.format(i))
		if i == 1:
			url = "https://www.dy2018.com/html/gndy/dyzz/"
		else:
			url = base_url.format(i)
		moveHref = getHref(url)
		print("休息2s后再進(jìn)行操作")
		time.sleep(2)
		for index,mhref in enumerate(moveHref):
			print('---- 正在處理第{}部電影----'.format(index+1))
			move = getPage(mhref)
			moves.append(move)
# 將電影信息寫入數(shù)據(jù)庫(kù)
	db = pymysql.connect(host='127.0.0.1',user='root', password='123456', port=3306, db='你的數(shù)據(jù)庫(kù)名稱')
	table = 'movies'
	i = 1
	for data in moves:
		keys = ', '.join(data.keys())
		values = ', '.join(['%s'] * len(data))
		sql = 'INSERT INTO {table}(id,{keys}) VALUES (null,{values})'.format(table=table, keys=keys, values=values)
		try:
			cursor = db.cursor()
			cursor.execute(sql, tuple(data.values()))
			print('本條數(shù)據(jù)成功執(zhí)行!')
			if i%10==0:
   				db.commit()
		except Exception as e:
   			print('將電影信息寫入數(shù)據(jù)庫(kù)發(fā)生異常!',repr(e))
   			db.rollback()
		cursor.close()
		i = i + 1
	db.commit()
	db.close()
	print('寫入數(shù)據(jù)庫(kù)完成！')

if __name__ == '__main__':
	spider()

CREATE TABLE `movies` (
  `id` bigint(20) NOT NULL AUTO_INCREMENT,
  `movie_name` varchar(255) DEFAULT NULL,
  `image_path` varchar(255) DEFAULT NULL,
  `screenshot` varchar(255) DEFAULT NULL,
  `translation` varchar(255) DEFAULT NULL,
  `movie_title` varchar(255) DEFAULT NULL,
  `movie_age` varchar(50) DEFAULT NULL,
  `movie_place` varchar(50) DEFAULT NULL,
  `category` varchar(100) DEFAULT NULL,
  `language` varchar(100) DEFAULT NULL,
  `subtitle` varchar(100) DEFAULT NULL,
  `release_date` varchar(50) DEFAULT NULL,
  `douban_score` varchar(50) DEFAULT NULL,
  `file_length` varchar(255) DEFAULT NULL,
  `director` varchar(100) DEFAULT NULL,
  `screenwriter` varchar(100) DEFAULT NULL,
  `stars` mediumtext,
  `tags` varchar(255) DEFAULT NULL,
  `introduction` mediumtext,
  `awards` text,
  `movie_url` varchar(255) DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;

python collectMovies.py

unindent does not match any outer indentation level

ssl.SSLEOFError: EOF occurred in violation of protocol
······
Max retries exceeded with url