def parse(self, response):
print(f'Processing {response.request.url}')
item = DoubanSpiderItem()
commentlist = Selector(
response=response).xpath('//div[@class="review-list "]/div')
for comm in commentlist:
cid = comm.xpath('./@data-cid').get()
user = comm.xpath('./div/header/a[2]/text()').get()
updatetime = comm.xpath('./div/header/span[2]/text()').get()
star = comm.xpath('./div/header/span[1]/@class').get()
title = comm.xpath('./div/div/h2/a/text()').get()
shorts = comm.xpath('./div/div/div/div/text()').getall()
shortfull = ''
for short in shorts:
shortfull += short.strip()
shortfull = shortfull[:-7].strip()
#print(f"{cid} : {shortfull} -END-")
item['cid'] = int(cid)
item['user'] = user
item['updatetime'] = updatetime
#print(star)
if star[:7] == 'allstar':
item['star'] = int(star[7:8])
else:
item['star'] = 0
item['title'] = title
item['short'] = shortfull
#print(item)
yield item
def parse(self,response):
print response
sel=Selector(response)
item=DoubanSpiderItem()
movie_name=sel.xpath('//span[@class="title"]/text()').extract()
star=sel.xpath('//div[@class="star"]/span/em/text()').extract()
quote=sel.xpath('//p[@class="quote"]/span[@class="inq"]/text()').extract()
item['movie_name']=[n.encode('utf-8') for n in movie_name]
item['star']=[n.encode('utf-8') for n in star]
item['quote']=[n.encode('utf-8') for n in quote]
yield item
next_page=sel.xpath('//div[@class="paginator"]/a/@href').extract()
for url in next_page:
url='http://movie.douban.com/top250'+url
yield Request(url,callback=self.parse_item)
def parse(self, response):
movies = Selector(response=response).xpath('//div[@class="hd"]')
for movie in movies:
item = DoubanSpiderItem()
title = movie.xpath('./a/span/text()').extract_first()
item['title'] = title
link = movie.xpath(
'./a/@href').extract_first() + '/comments?status=P'
yield scrapy.Request(url=link,
meta={'item': item},
callback=self.parse2)
def parse_item(self, response):
sel = Selector(response)
item = DoubanSpiderItem()
sites = sel.xpath('//div[@class="info"]')
for site in sites:
item['movie_name'] = site.xpath(
'div[@class="hd"]/a/span[1]/text()').extract()
item['movie_star'] = site.xpath(
'div[@class="bd"]/div/span[2]/text()').extract()
item['movie_quote'] = site.xpath(
'div[@class="bd"]/p[@class="quote"]/span/text()').extract()
yield item
def parse_item(self, response):
print response
sel = Selector(response)
item = DoubanSpiderItem()
movie_name = sel.xpath('//span[@class="title"][1]/text()').extract()
star = sel.xpath('//div[@class="star"]/span/em/text()').extract()
quote = sel.xpath(
'//p[@class="quote"]/span[@class="inq"]/text()').extract()
item['movie_name'] = [n.encode('utf-8') for n in movie_name]
item['star'] = [n.encode('utf-8') for n in star]
item['quote'] = [n.encode('utf-8') for n in quote]
yield item
def parse_item(self,response):
print response
sel=Selector(response)
item=DoubanSpiderItem()
soup=BeautifulSoup(response.url.text,'lxml')
movie_name=sel.xpath('//span[@class="title"][0]/text()').extract()
star=sel.xpath('//span[@class="rating_num"]/text()').extract()
quote=soup.find_all('p',class_='quote').find('span',class_='inq').text()
item['movie_name']=[n.encode('utf-8') for n in movie_name]
item['star']=[n for n in star]
item['quote']=[n.encode('utf-8') for n in quote]
yield item
def parse_item(self, response):
sel = Selector(response)
item = DoubanSpiderItem()
movie_name = sel.xpath('//span[@class="title"][1]/text()').extract()
# //*[@id="content"]/div/div[1]/ol/li[1]/div/div[2]/div[2]/div/span[2]
# star = sel.xpath('//div[@class="star"]/span/em/text()').extract()
star = sel.xpath('//div[@class="star"]/span[@class="rating_num"]/text()').extract()
quote = sel.xpath('//p[@class="quote"]/span[@class="inq"]/text()').extract()
item['movie_name'] = [n.encode('utf-8').decode('utf-8') for n in movie_name]
item['star'] = [n.encode('utf-8').decode('utf-8') for n in star]
item['quote'] = [n.encode('utf-8').decode('utf-8') for n in quote]
yield item
def parse_short(self, response):
meta = deepcopy(response.meta)
short_answers, recommendation_index, useful_num = [], [], []
num_for_short = meta[
"num_for_short"] if meta["num_for_short"] < 501 else 500
for count in range(0, num_for_short, 20):
short_url = self.short_url.format(meta["id"], count)
print("short_url", short_url)
try:
res = self.get_shorturl_content(short_url)
if len(re.findall(r'"code":112', str(res))) > 0:
self.crawler.engine.close_spider(self, '程序异常，停止爬虫!')
print('！！！111程序异常，停止爬虫！！！，状态码是：', response.status)
else:
short_answers_temp = [
emoji.demojize(i["content"]) for i in res["comments"]
]
recommendation_index_temp = [
i["rating"]["value"] for i in res["comments"]
]
useful_num_temp = [
i["useful_count"] for i in res["comments"]
]
short_answers.extend(short_answers_temp)
recommendation_index.extend(recommendation_index_temp)
useful_num.extend(useful_num_temp)
except Exception as e:
logger.info(e)
continue
info = DoubanSpiderItem()
info["url"] = meta["url"]
info["movie_id"] = meta["id"]
info["name"] = meta["name"]
info["scriptwriters"] = meta["scriptwriters"]
info["directors"] = meta["directors"]
info["actors"] = meta["actors"]
info["type"] = meta["type"]
info["region"] = meta["region"]
info["language"] = meta["language"]
info["duration"] = meta["duration"]
info["release_date"] = meta["release_date"]
info["alias"] = meta["alias"]
info["source"] = meta["source"]
info["description"] = meta["description"]
info["short_answers"] = short_answers
info["recommendation_index"] = recommendation_index
info["useful_num"] = useful_num
yield info
def parse(self, response):
item = DoubanSpiderItem()
#selector = Selector(response)
#all_movie = selector.xpath('//div[@class="info"]')
for r in response.css('div.item'):
item['rank'] = r.css('div.pic em::text').extract()
item['name'] = r.css(
'div.info div.hd a span.title::text').extract_first()
item['score'] = r.css(
'div.info div.bd div.star span.rating_num::text').extract()
yield item
next_url = response.css(
'div.paginator span.next a::attr(href)').extract()
if next_url:
next_url = "https://movie.douban.com/top250" + next_url[0]
print(next_url)
yield scrapy.Request(next_url, headers=self.headers)
def parse_detail(self, response):
print "detail url:" + response.url
_name = response.css('div#content h1 span:first-child').xpath(
'.//text()').extract()[0]
name = _name
score = response.css(
'div#interest_sectl div.rating_self strong.rating_num').xpath(
'.//text()').extract()[0]
_summary = response.css('div.related-info div.indent span').xpath(
'.//text()').extract()[0]
summary = _summary.strip()
_actors = response.css('div#info span.actor span.attrs a').xpath(
'.//text()').extract()
_types = response.css('div#info >span[property="v:genre"]').xpath(
'.//text()').extract()
release_time = response.css(
'div#info >span[property="v:initialReleaseDate"]').xpath(
'.//text()').extract()[0]
if _types:
types = ','.join(_types)
else:
types = None
if _actors:
actors = ','.join(_actors)
else:
actors = None
# print name.encode('utf-8')
# print score
# print summary.encode('utf-8')
# print actors.encode('utf-8')
# print types.encode('utf-8')
# print release_time.encode('utf-8')
item = DoubanSpiderItem()
item['name'] = name
item['score'] = score
item['summary'] = summary
item['types'] = types
item['actors'] = actors
item['src_url'] = response.url
item['release_time'] = release_time
yield item
def parse_item(self, response):
print response
sel = Selector(response)
item = DoubanSpiderItem()
item['movie_name'] = sel.xpath(
'//span[@class="title"][1]/text()').extract()
item['star'] = sel.xpath(
'//div[@class="star"]/span[@class="rating_num"]/text()').extract()
item['quote'] = sel.xpath(
'//p[@class="quote"]/span[@class="inq"]/text()').extract()
yield item
nextPage = sel.xpath(
'//div[@class="paginator"]/span[@class="next"]/a/@href').extract(
)[0]
print nextPage
if nextPage:
next_url = 'https://movie.douban.com/top250' + nextPage
yield Request(next_url, callback=self.parse_item)
def parse_item(self, response):
rank_No = response.xpath("//span[@class='top250-no']/text()").get()
rank = rank_No.split('.')[1]
title = response.xpath("//h1/span/text()").get()
year_text = response.xpath("//span[@class='year']/text()").get()
year = re.sub(r'\(|\)', '', year_text)
infos = response.xpath("//div[@id='info']/span")
director = infos[0].xpath(".//a/text()").get()
screenwriter_list = infos[1].xpath(".//a/text()").getall()
screenwriter = ','.join(screenwriter_list)
stars_list = infos[2].xpath(".//a/text()").getall()
stars = ','.join(stars_list)
types_list = response.xpath("//div[@id='info']/span[@property='v:genre']/text()").getall()
types = ','.join(types_list)
runtime = response.xpath("//span[@property='v:runtime']/text()").get()
IMDb = response.xpath("//div[@id='info']/a[@rel='nofollow']/@href").get()
origin_url = response.url
pub_time = response.xpath("//span[@property='v:initialReleaseDate']/@content").get()
others = response.xpath("//div[@id='info']/text()").getall()
country, language, *_ = [x for x in list(map(lambda x: re.sub(r"\s|/", '', x), others)) if x]
item = DoubanSpiderItem(rank=rank,
title=title,
year=year,
director=director,
screenwriter=screenwriter,
stars=stars,
types=types,
runtime=runtime,
IMDb=IMDb,
origin_url=origin_url,
pub_time=pub_time,
)
yield item
def parse_item(self, response):
pre = 'https://movie.douban.com/top250'
print(response)
sel = Selector(response)
item = DoubanSpiderItem()
movie_name = sel.xpath('//span[@class="title"][1]/text()').extract()
star = sel.xpath(
'//div[@class="star"]/span[@class="rating_num"]/text()').extract()
quote = sel.xpath(
'//p[@class="quote"]/span[@class="inq"]/text()').extract()
item['movie_name'] = [n for n in movie_name]
item['star'] = [n for n in star]
item['quote'] = [n for n in quote]
urls = sel.xpath('//span[@class="next"]/a/@href').extract()
for i in range(len(urls)):
print(i)
print(pre + urls[i])
yield Request(pre + urls[i],
headers=self.headers,
callback=self.parse_item)
yield item
def parse(self, response):
item = DoubanSpiderItem()
name = response.css()
