def parse_url(self, response):
links = response.xpath('//a[@class="elemRelative"]/@href').extract()
for link in links:
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse(self, response):
word = response.meta.get("keyword")
show_word, uk_phonetic, us_phonetic = '', '', ''
di_title = response.xpath(
'//div[@class="di-title"]//span[@class="hw dhw"]')
if di_title:
show_word = ''.join(di_title[0].xpath("./text()").extract())
uk_span = response.xpath(
'//div[@class="pos-header dpos-h"]//span[@class="uk dpron-i "]/span[@class="pron dpron"]'
)
if uk_span:
uk_phonetic = ''.join(uk_span[0].xpath('.//text()').extract())
if uk_phonetic:
uk_phonetic = "[" + uk_phonetic.strip('/') + "]"
us_span = response.xpath(
'//div[@class="pos-header dpos-h"]//span[@class="us dpron-i "]/span[@class="pron dpron"]'
)
if us_span:
us_phonetic = ''.join(uk_span[0].xpath('.//text()').extract())
if us_phonetic:
us_phonetic = "[" + us_phonetic.strip('/') + "]"
item = SpiderframeItem()
item['title'] = word # title 字段 存单词
item['category'] = show_word # category 存显示的单词
item['content'] = uk_phonetic # content 字段存 英式英语
item['item_name'] = us_phonetic # category 字段 美式英语
yield item
def parse(self, response):
links = response.xpath('//div[@class="box"]//ul/li//a//@href').extract()
for link in links:
item = SpiderframeItem()
item['url'] = "http://www.enet.gr/"+link
# print(item)
yield item
def parse_link(self, response):
links = response.xpath('//h2/a/@href').extract()
for link in links:
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse_url(self, response):
links = response.xpath('//article/a//@href').extract()
for link in links:
if "https://" in link:
item = SpiderframeItem()
item['url'] = link
yield item
def parse(self, response):
show_word_r = response.xpath(
'//div[@class="webtop"]/h1/text()').extract()
if show_word_r:
show_word = show_word_r[0]
else:
show_word = ''
ph_en_r = response.xpath(
'//div[@class="webtop"]/span[@class="phonetics"]/div[@class="phons_br"]/span/text()'
).extract()
if ph_en_r:
ph_en = ph_en_r[0]
else:
ph_en = ''
ph_am_r = response.xpath(
'//div[@class="webtop"]/span[@class="phonetics"]/div[@class="phons_n_am"]/span/text()'
).extract()
if ph_am_r:
ph_am = ph_am_r[0]
else:
ph_am = ''
item = SpiderframeItem()
item['title'] = response.meta.get("keyword") # title 字段 存单词
item['category'] = show_word # category 存显示的单词
item['content'] = ph_en # content 字段存 英式英语
item['item_name'] = ph_am # category 字段 美式英语
return item
def parse_url(self, response):
links = response.xpath('//div[@class="news"]/a/@href').extract()
for link in links:
link = "http://www.hurriyetdailynews.com" + link
item = SpiderframeItem()
item['url'] = link
yield item
def parse_url(self, response):
links = response.xpath('//a[@class="item"]/@href').extract()
for link in links:
link = "https://www.masrawy.com" + link
item = SpiderframeItem()
item['url'] = link
yield item
def parse(self, response):
# sentens1 = response.xpath('//div[@class="layout sort"]//li//text()').extract()
# sentens2 = response.xpath('//div[@class="layout patt"]//li//text()').extract()
# sentens3 = response.xpath('//div[@class="layout auth"]//li//text()').extract()
# sentenses = sentens1 + sentens2 + sentens3
# for sentens in sentenses:
# if (sentens >= u'\u0041' and sentens <= u'\u005a') or (sentens >= u'\u0061' and sentens <= u'\u007a'):
# md = md5(sentens)
# item = SpiderframeItem()
# item['content'] = sentens
# item['title'] = response.meta.get("keyword")
# item['category'] = 'dict'
# item['item_id'] = md
# yield item
# 抓取读音
word = response.url.split("=")[-1]
word_tag = response.xpath(
'//div[@class="word-cont"]/h1/text()').extract() # 显示单词
if word_tag:
phonetic = response.xpath('//div[@class="phonetic"]/span')
en_phonetic, am_phonetic, phonetic_word = '', '', []
if phonetic:
for item in phonetic:
pronounce_lang = item.xpath(
"./text()").extract() # 根据标签区分英式和美式
if pronounce_lang:
pronounce_text = ''.join(pronounce_lang).strip()
pronounce_text = pronounce_text.replace(" '",
'').replace(
"’", '')
if pronounce_text == "英":
en_phonetic = ''.join(
item.xpath(
'./bdo[@lang="EN-US"]/text()').extract())
en_word = ''.join(
item.xpath('./i[1]/@naudio').extract())
if en_word:
phonetic_word.append(en_word.split("=")[-1])
elif pronounce_text == "美":
am_phonetic = ''.join(
item.xpath(
'./bdo[@lang="EN-US"]/text()').extract())
am_word = ''.join(
item.xpath('./i[1]/@naudio').extract())
if am_word:
phonetic_word.append(am_word.split("=")[-1])
if phonetic_word:
phonetic_word = phonetic_word[0]
else:
phonetic_word = ''
item = SpiderframeItem()
item['title'] = word # title 字段 存单词
# item['category'] = word_tag[0] # category 存显示的单词
item['category'] = phonetic_word # category 音标的单词
item['content'] = en_phonetic # content 字段存 英式英语
item['item_name'] = am_phonetic # category 字段 美式英语
yield item
def parse_link(self, response):
links = response.xpath(
'//a[contains(@class, "url track-click")]/@href').extract()
for link in links:
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse_url(self, response):
links = response.xpath(
'//a[contains(@class, "dre-item__title")]/@href').extract()
for link in links:
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse_url(self, response):
links = response.xpath('//h3/a/@href').extract()
for link in links:
link = "https://www.alittihad.ae" + link
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse(self, response):
links = response.xpath(
'//a[@class="iframe cboxElement"]/@href').extract()
for link in links:
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse(self, response):
nodes = response.xpath('//*[@id="tmTable"]/div/div[2]/span/span')
for node in nodes:
sentence = ''.join(node.xpath(".//span/text()").extract())
item = SpiderframeItem()
item['url'] = response.url
item['content'] = sentence
yield item
def parse_url(self, response):
links = response.xpath('//a[@class="ankeiler__link"]/@href').extract()
for link in links:
# print(link)
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse_url(self, response):
links = response.xpath('//a[@class="c-teaser__link"]/@href').extract()
for link in links:
link = "https://www.gp.se" + link
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse_url(self, response):
links = response.xpath(
'//div[@class="field field-name-field-webrubrik"]/a/@href'
).extract()
for link in links:
item = SpiderframeItem()
item['url'] = "https://www.information.dk" + link
# print(item)
yield item
def parse(self, response):
patterns = response.xpath(
'//a[@class="differentTall"]/@href').extract()
for pattern in patterns:
link = "http://www.alkhaleej.ae" + pattern
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse_url(self, response):
links = response.xpath('//h3/a/@href').extract()
for link in links:
link = urllib.parse.quote(link)
link = "https://www.tagesanzeiger.ch" + link
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse_url(self, response):
links = response.xpath(
'//div[contains(@class, "art")]//a/@href').extract()
for link in links:
if "https://jyllands-posten.dk" in link:
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse_url(self, response):
page = response.text
json_content = demjson.decode(page)
json_contents = json_content["data"]
json_list = json_contents["item"]
cdn_url = json_list.get("cdn_url")
large_mp4 = cdn_url.get("large")
item = SpiderframeItem()
item["url"] = large_mp4
yield item
def parse(self, response):
description = response.xpath(
'/html/body/section[2]/section[1]/section[1]/p/text()').extract()
paragraph = response.xpath(
'/html/body/section[2]/section[1]/section[1]/article/p/text()'
).extract()
content = ' '.join(description + paragraph).replace('\n', '')
item = SpiderframeItem()
item['url'] = response.url
item['content'] = content
return item
def parse(self, response):
title = response.xpath(
'//h1[contains(@class, "title")]/text()').extract()
# subtitle = response.xpath('//p[@class="subtitle"]/text()').extract()
content = response.xpath('//section/p/text()').extract()
item = SpiderframeItem()
item['url'] = response.url
item['category'] = response.url.split('/')[2].split('.')[0]
item['title'] = ''.join(title)
item['content'] = ''.join(content)
yield item
def parse(self, response):
title = response.xpath('//h1/text()').extract()
content = response.xpath('//p/text()').extract()
item = SpiderframeItem()
# item['id'] = 11111111111111
item['url'] = response.url
item['category'] = response.url.split('/')[-2]
item['title'] = ''.join(title)
item['content'] = ''.join(content)
# print(item)
yield item
def parse_content(self, response):
resp = demjson.decode(response.text)
data = resp.get("items", [])
for v1 in data.values():
for v2 in v1.values():
if type(v2) is list and v2:
data1=v2[0]
if data1.get("target"):
expandedUri = data1["target"]["expandedUri"]
item = SpiderframeItem()
item['url'] = expandedUri
yield item
def parse(self, response):
title = response.xpath('//h1/text()').extract()
content = response.xpath('//p//text()').extract()
content = ''.join(content)
content = content.replace("\n", " ")
content = content.replace("\t", " ")
item = SpiderframeItem()
item['url'] = response.url
item['category'] = response.url.split('/')[3]
item['title'] = ''.join(title)
item['content'] = ''.join(content)
yield item
def parse_link(self, response):
next_urls = response.xpath('//li[@class="nxtnav "]/a/href')
for next_url in next_urls:
yield scrapy.Request(url=next_url,
callback=self.parse_link,
dont_filter=True)
links = response.xpath('//div[@class="mask-title"]/a/@href').extract()
for link in links:
item = SpiderframeItem()
item['url'] = link
# print(item)
yield item
def parse(self, response):
title = response.xpath('//h2[@class="page-title"]/text()').extract()
content = response.xpath('//p/text()').extract()
content = ''.join(content)
content = content.replace("\n", " ")
content = content.replace("\t", " ")
item = SpiderframeItem()
item['url'] = response.url
item['category'] = response.url.split('/')[-2]
item['title'] = ''.join(title)
item['content'] = content
# print(item)
yield item
def parse_item(self, response):
links = response.xpath(
"//section[(contains(@class, 'sequence'))]//a/@href").extract()
for url in links:
item = SpiderframeItem()
item['url'] = url
yield item
next_url = response.xpath(
'//section/div/nav[1]/a[@rel="next"]/@href').extract()
if next_url:
yield scrapy.Request(url=next_url[0],
callback=self.parse_item,
dont_filter=True)
def parse_content(self, response):
lis = response.xpath('//span//tr/td/table//tr[3]/td/table//tr')
for li in lis:
lis_text = li.xpath('.//td[not(@class)]//text()').extract()
sentens = "".join(lis_text)
if "未完全匹配句对" not in sentens and sentens != "":
sentens = sentens.strip()
md = md5(sentens)
item = SpiderframeItem()
item['content'] = sentens
item['title'] = response.meta.get("keyword")
item['category'] = 'cnki'
item['item_id'] = md
yield item
