def parse(self, response):
item = MyscrapyItem()
movies = response.xpath('//div[@class="info"]')
for each in movies:
title = each.xpath(
'//div[@class="hd"]/a/span[@class="title"]/text()').extract()
content = each.xpath('//div[@class="bd"]/p/text()').extract()
score = each.xpath(
'//div[@class="bd"]/div[@class="star"]/span[@class="rating_num"]/text()'
).extract()
ratetotal = each.xpath(
'//div[@class="bd"]/div[@class="star"]/span[4]/text()'
).extract()
info = extract.xpath(
'//div[@class="bd"]/p[@class="quote"]/span[@class="inq"]/text()'
).extract()
item['title'] = title[0]
item['content'] = ';'.join(content)
item['score'] = score[0]
item['ratetotal'] = ratetotal[0]
item['info'] = info[0]
yield item
if self.start <= 225:
self.start += 25
yield scrapy.Request(self.url + str(self.start) + self.end,
callback=self.parse)
def parse(self, response):
i = 0
for item in response.xpath(
"//div[@class='seo-recommended-notes']/div"):
i = i + 1
myItem = MyscrapyItem()
myItem['author'] = item.xpath(
"./a[@class='author']/span/text()").extract()[0]
print("作者：" + myItem['author'])
myItem['author_icon_url'] = item.xpath(
"./a[@class='author']/@href").extract()[0]
myItem['blog_title'] = item.xpath(
"./a[@class='title']/text()").extract()[0]
print("标题：" + myItem['blog_title'])
myItem['content_summary'] = item.xpath("./p/text()").extract()[0]
print("内容：" + myItem['content_summary'])
myItem['content_url'] = item.xpath(
"./a[@class='title']/@href").extract()[0]
print("url:" + self.base_url + myItem['content_url'])
time.sleep(1)
if myItem['content_url'] not in self.viewed:
self.url = myItem['content_url']
self.viewed.append(self.url)
if (i == len(
response.xpath(
"//div[@class='seo-recommended-notes']/div"))):
self.page_order = self.page_order + 1
yield self.parse_more()
def parse(self, response):
names = response.xpath(
'//div[@class ="channel-detail movie-item-title"]/@title').extract(
)
scores = [
score.xpath('string(.)').extract_first()
for score in response.xpath(
'//div[@class = "channel-detail channel-detail-orange"]')
]
# for score in scores_div:
# scores.append(score.xpath('string(.)').extract_first())
# use dictionary to push item
# for name, score in zip(names, scores):
# # print(name, ':', score)
# yield {"name": name, "score": score}
# use object to push item
item = MyscrapyItem()
for name, score in zip(names, scores):
item['name'] = name
item['score'] = score
if response.url.find('catId=2') != -1:
item['type'] = 'comedy'
elif response.url.find('catId=3') != -1:
item['type'] = 'romantic'
yield item
def parse(self,response):
# current_url = response.url #爬取时请求的URL
# body = response.body #返回的Html
# unicode_body = response.body_as_uncode()#返回的html unicode编码
item = MyscrapyItem()
selector = scrapy.Selector(response)
#sites = hxs.select('//ul/li/div/a/img/@src').extract()
books = selector.xpath('//div[@class="bd doulist-subject"]')
for book in books:
#print(item)
title = book.xpath('div[@class="title"]/a/text()').extract()[0]
rate = book.xpath('div[@class="rating"]/span[@class="rating_nums"]/text()').extract()[0]
author = book.xpath('div[@class="abstract"]/text()').extract()[0]
title = title.replace(' ','').replace('\n','')
author = author.replace(' ','').replace('\n','')
item['title'] = title
item['rate'] = rate
item['author'] = author
#print(title)
#print(rate)
#print(author)
#print('\n')
yield item
nextpage = selector.xpath('//span[@class="next"]/link/@href').extract()
if nextpage:
next = nextpage[0]
yield scrapy.http.Request(next,callback=self.parse)
def parse(self, response):
quotes = response.xpath("//div[@class='quote']/span[@class='text']")
for x in quotes:
item = MyscrapyItem()
title = x.xpath(".//text()").get()
item['title'] = title
yield item
def parse(self, response):
movie = MyscrapyItem()
movie['name'] = response.xpath(
'//div[@id="content"]/h1/span[1]/text()')[0].extract()
movie['director'] = response.xpath(
'//div[@id="info"]/span[@class="attrs"]/text()')[0].extract()
actor_list = []
actor_list.extend(response.xpath('//span[@class="actor"]'))
def parse(self, response):
list = response.xpath('//div[@class="li_txt"]')
for element in list:
item = MyscrapyItem()
name = element.xpath('./h3/text()').extract()
title = element.xpath('./h4/text()').extract()
info = element.xpath('./p/text()').extract()
item['name'] = name[0].strip()
item['title'] = title[0].strip()
item['info'] = info[0].strip()
yield item
def parse(self, response):
# print("请求："+response.xpath("//ul[@class='note-list']/li").extract()[0])
for i in response.xpath("//ul[@class='note-list']/li"):
print("数量：" + str(
len(response.xpath("//ul[@class='note-list']/li").extract())))
item = MyscrapyItem()
try:
item['_id'] = i.xpath("./@id").extract()[0]
except Exception as e:
print(e)
return
try:
# text()
item['blog_title'] = i.xpath(
".//div[@class='content']/a/text()").extract()[0]
except Exception as e:
print(e)
return
try:
item['content_url'] = self.get_full_url(
i.xpath(".//div[@class='content']/a/@href").extract()[0])
except Exception as e:
item['content_url'] = ''
try:
item['content_summary'] = i.xpath(
".//div[@class='content']/p/text()").extract()[0]
except Exception as e:
item['content_summary'] = ''
try:
item['content_figure_url'] = self.get_full_url(
i.xpath("./a/img/@src").extract()[0])
except Exception as e:
item['content_figure_url'] = ''
try:
item['author'] = i.xpath(
".//div[@class='author']/div/a/text()").extract()[0]
except Exception as e:
item['author'] = ''
try:
item['date'] = i.xpath(
".//div[@class='author']/div/span/@data-shared - at"
).extract()[0]
except Exception as e:
item['date'] = ''
try:
item['author_icon_url'] = self.get_full_url(
i.xpath(".//div[@class='author']/a/@href").extract()[0])
except Exception as e:
item['author_icon_url'] = ''
yield item
def parse(self, response):
qiubai = MyscrapyItem()
# print 'start $$$$$$$$$$$$$$$$$$$$$$$'
# print response.xpath('//div[@class="bai"]/a/@href|//div[@class="du"]/a/@href').extract()
# print 'end $$$$$$$$$$$$$$$$$$$$$$$'
a = 0
for item in response.xpath(
'//div[@class="bai"]/a/@href|//div[@class="du"]/a/@href'
).extract():
if a > 1:
break
a = a + 1
yield scrapy.Request(url=item, callback=self.second_parse)
def parse(self, response):
items = []
soup = BeautifulSoup(response.text, 'lxml')
sectionList = soup.find_all(class_='stream-list__item')
for section in sectionList:
title = section.find(class_='title').a.get_text()
quote = section.find(class_='excerpt wordbreak hidden-xs').get_text().strip()
time = section.find(class_='col-xs-10').get_text().strip()[-12:-2]
itemLoader = ItemLoader(item=MyscrapyItem(), response=response)
itemLoader.add_value('title', title)
itemLoader.add_value('quote', quote)
itemLoader.add_value('time', time)
items.append(itemLoader.load_item())
return items
def parse(self, response):
tr_list = response.xpath(
'//div[@class="greyframe"]/table[2]/tr/td/table/tr')
for tr in tr_list:
item = MyscrapyItem()
item['num'] = tr.xpath('./td[1]/text()').extract_first()
item['title'] = tr.xpath('./td[2]/a[2]/text()').extract_first()
item['href'] = tr.xpath('./td[2]/a[2]/@href').extract_first()
item['status'] = tr.xpath('./td[3]/span/text()').extract_first()
item['name'] = tr.xpath('./td[4]/text()').extract_first()
item['publish_date'] = tr.xpath('./td[5]/text()').extract_first()
yield scrapy.Request(item['href'],
callback=self.parse_detail,
meta={'item': item})
#构造下一页请求,翻页
next_url = response.xpath('//a[text()=">"]/@href').extract_first()
if next_url is not None:
yield scrapy.Request(next_url, callback=self.parse)
def parse(self, response):
titles = response.xpath(
'//*[@id="main_content"]/div[2]/ul/li/dl/dt[2]/a/text()').extract(
)
authors = response.css('.writing::text').extract()
previews = response.css('.lede::text').extract()
items = []
# loop
for idx in range(len(titles)):
item = MyscrapyItem()
item['title'] = titles[idx]
item['author'] = authors[idx]
item['preview'] = previews[idx]
items.append(item)
return items
def parse_travellist(self, response):
"""得到每一个地点的游记列表"""
# print("into parse_travellist************************************")
if response.status == 200 :
print("enter")
res = response.text
content = json.loads(res)
s = content.get('list', 0)
page_info = content.get('page',0)
#提取下一页的请求参数
next = re.compile(r'<a class="pi pg-next" href="/yj/(\d+)/1-0-(\d+).html" title')
next = re.search(next,page_info)
if s:
s = "<html>" + s + "</html>"
html = etree.HTML(s)
lis = html.xpath('//div[@class="tn-item clearfix"]')
for li in lis[:]:
href1 = li.xpath('.//a[@class="title-link"]//@href')[0]
title = li.xpath('.//a[@class="title-link"]/text()')#('./div[@class="tn-wrapper"]/dl/dt/a/text()')
content = li.xpath('./div[@class="tn-wrapper"]/dl/dd/a/text()')
zan = li.xpath('./div[@class="tn-wrapper"]/div/span[@class="tn-ding"]/em/text()')
user_name = li.xpath('./div[@class="tn-wrapper"]/div/span[@class="tn-user"]/a/text()')
item = MyscrapyItem()
item['title'] = title[0] if title else ''
item['content'] = content[0] if content else ''
item['zan'] = zan[0] if zan else ''
item['user_name'] = user_name[0] if user_name else ''
yield item
# url = 'http://www.mafengwo.cn' + href1
# yield Request(url, callback=self.parse_detail, dont_filter=False)
if next:
next_page = next.group(1) #获取参数midde的值
next_num = next.group(2) #获取参数page的值
every_page_params = self.params
every_page_params['mddid'] = next_page
every_page_params['page'] = next_num
yield FormRequest(self.travel_url, callback=self.parse_travellist,dont_filter=False, formdata=every_page_params)
else:
logging.warning(f"parse_travellist失败！：{response.status}")
# def parse_detail(self, response):
# """每一个游记的详细内容"""
# print(response.text)
def parse(self, response):
# 创建MyscrapyItem类的实例
item = MyscrapyItem()
sectionList = response.xpath('//*[@id="all"]/div[1]/section').extract()
for section in sectionList:
bs = BeautifulSoup(section, 'lxml')
articleDict = {}
a = bs.find('a')
articleDict['title'] = a.text
articleDict['href'] = 'https://geekori.com/' + a.get('href')
p = bs.find('p', class_='excerpt')
articleDict['abstract'] = p.text
# 为MyscrapyItem对象的3个属性赋值
item['title'] = articleDict['title']
item['href'] = articleDict['href']
item['abstract'] = articleDict['abstract']
# 本例只保存抓取的第1条博文先关信息，所以迭代一次后退出for循环
break
# 返回MyscrapyItem对象
return item
def parse(self, response):
items = []
sectionList = response.xpath('//*[@id="all"]/div[1]/section').extract()
for section in sectionList:
bs = BeautifulSoup(section, 'lxml')
articleDict = {}
a = bs.find('a')
articleDict['title'] = a.text
articleDict['href'] = 'https://geekori.com/' + a.get('href')
p = bs.find('p', class_='excerpt')
articleDict['abstract'] = p.text
itemLoader = ItemLoader(item=MyscrapyItem(), response=response)
itemLoader.add_value('title', articleDict['title'])
itemLoader.add_value('href', articleDict['href'])
itemLoader.add_value('abstract', articleDict['abstract'])
items.append(itemLoader.load_item())
return items
def parse(self, response):
#开始爬取
print("spider start")
#取出所有<li>标签中style=_width:183px;的标签
node_list = response.xpath("//li[@style='_width:183px;']")
#遍历list
for node in node_list:
# 创建item字段对象用来存储信息
item = MyscrapyItem()
# extract() : 将xpath对象转换为Unicode字符串
novelName = node.xpath("./a/@alt").extract()
authorName = node.xpath("./a/label/text()").extract()
novelContent = node.xpath("./a/@href").extract()
#对的到的信息进行一点加工,并放入item中
item['novelName'] = novelName[0].split(" ")[0]
item['authorName'] = authorName[0]
item['novelContent'] = "http://www.jjwxc.net/" + novelContent[0]
yield item
def parse(self, response):
item = MyscrapyItem()
tr_list = response.xpath(
"//div[@class='greyframe']/table[2]/tr/td/table/tr")
for tr in tr_list:
item["title"] = tr.xpath(
"./td[2]/a[@class='news14']/@title").extract_first()
item["href"] = tr.xpath(
"./td[2]/a[@class='news14']/@href").extract_first()
item["who"] = tr.xpath("./td[4]/text()").extract_first()
item["time"] = tr.xpath("./td[5]/text()").extract_first()
yield scrapy.Request(item["href"],
callback=self.parse_detail,
meta={"item": deepcopy(item)})
next_url = response.xpath(
"//div[@class='pagination']/a[@text()='>']/@href").extract_first()
if next_url is not None:
yield scrapy.Request(next_url, callback=self.parse)
yield item
def parse(self, response):
data = response.body
soup = BeautifulSoup(data, "lxml")
data = soup.find("table", class_="tablelist")
trs = data.select("tr")
for tr in trs[1:-2]:
td = tr.select("td")
item = MyscrapyItem()
item["title"] = td[0].string
item["position"] = td[3].string
item["date"] = td[4].string
yield item
div = soup.find('div', class_="pagenav")
next = div.find("a", id="next")
next_url = next['href']
# print(next_url)
next_url = "https://hr.tencent.com/" + next_url
yield scrapy.Request(next_url, callback=self.parse)
def parse(self, response):
# print(response)
content = response.body.decode('utf-8')
# with open('youbain.html','w',encoding='utf-8')as fp:
# fp.write(content)
#提取数据：
# print(content)
tree = etree.HTML(content)
cell_list = tree.xpath('//div[@class="cinema-cell"]')
for cell in cell_list:
#影院名称：
item = MyscrapyItem()
name = cell.xpath('./div[@class="cinema-info"]/a/text()')[0]
item['name'] = name
#地址：
adress = cell.xpath('./div[@class="cinema-info"]/p/text()')[0]
item['adress'] = adress
yield item
def parse(self, response):
try:
print 'url : ', response.url
urls = response.xpath(
'/html/body/div[8]/div/div[3]/img/@src').extract()
title = response.xpath(
'/html/body/div[8]/div/div[3]/h1/text()').extract()
item = MyscrapyItem()
item['title'] = title
item['urls'] = urls
yield item
page_urls = response.xpath(
'/html/body/div[8]/div/ul/span/a/@href').extract()
print len(page_urls)
for url in page_urls:
if str(url).startswith('http') or str(url).startswith('HTTP'):
full_url = url
else:
full_url = response.urljoin(url)
yield Request(url=full_url, callback=self.parse)
except Exception, e:
print "ERROR : ", e
def parse(self, response):
blogs = response.xpath("//div[@class='post_item_body']")
for b_item in blogs:
item = MyscrapyItem()
item["title"] = b_item.xpath(
"./h3/a[@class='titlelnk']/text()").extract()[0].strip()
item["link"] = b_item.xpath(
"./h3/a[@class='titlelnk']/@href").extract_first().strip()
item["discribe"] = b_item.xpath(
"./p[@class='post_item_summary']/text()").extract_first(
).strip()
item["author"] = b_item.xpath(
"./div[@class='post_item_foot']/a[@class='lightblue']/text()"
).extract_first().strip()
item["comment"] = b_item.xpath(
"./div[@class='post_item_foot']/span[@class='article_comment']/a[@class='gray']/text()"
).extract_first().strip()
yield item
next_links = response.xpath("//div[@class='pager']/a[last()]")
for next_link in next_links:
if next_link.xpath("./text()").extract_first() == 'Next >':
next_link_href = next_link.xpath("./@href").extract()[0]
yield self.make_requests_from_url(u"https://www.cnblogs.com" +
next_link_href)
def parse(self, response):
for sel in response.xpath(
'//div[@class="mod-info-flow"]/div/div[@class="mob-ctt"]'):
item = MyscrapyItem()
item['title'] = sel.xpath('h3/a/text()')[0].extract()
print(item['title'])
