def start_requests(self):
for tag in self.taglist:
url = 'https://pacaio.match.qq.com/openapi/json?key=' + tag + ':' + spiderUtil.get_time(
)[:-9].replace("-", "") + '&num=50'
yield scrapy.Request(url=url,
callback=self.parsepage,
headers=self.header)
def parsebody(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath(
"//div[@class='content-article']/p//text()").extract()
content = "".join(content_arr).strip()
except:
spiderUtil.log_level(7, response.url)
source = "https://news.qq.com/"
try:
if content != "" and str(
response.meta["public_time"]).startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = response.meta["public_time"]
item["url"] = response.url
item["title"] = response.meta["title"]
item["author"] = response.meta["author"]
item["html_size"] = html_size
item["crawl_time"] = spiderUtil.get_time()
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath("""//div[contains(@id,'detail')]//p/text()""").extract()
content = "".join(content_arr)
except:
spiderUtil.log_level(7, response.url)
source = "http://www.xinhuanet.com/"
try:
if content != "" and str(response.meta["public_time"]).startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = response.meta["public_time"]
item["url"] = response.url
item["title"] = response.meta["title"]
item["author"] = response.meta["author"]
item["html_size"] = html_size
item["crawl_time"] = spiderUtil.get_time()
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath(
"""//article//p//text()""").extract()
content = "".join(content_arr)
except:
spiderUtil.log_level(7, response.url)
source = "http://news.sohu.com/"
try:
if content != "" and str(
response.mete['public_time']).startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["public_time"] = response.mete['public_time']
item["url"] = response.mete['url']
item["title"] = response.mete['title']
item["author"] = response.mete['author']
item["source"] = source
item["content"] = content
item["html_size"] = html_size
item["crawl_time"] = spiderUtil.get_time()
# print(self.item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse_item_news_list(self, response):
news_url_arr = response.xpath("//a/@href").extract()
for news_url in news_url_arr:
if news_url.endswith(".html") and "jhtj" not in news_url:
if spiderUtil.get_time().replace("-", "")[:8] in news_url:
time.sleep(random.uniform(1, 2))
yield scrapy.Request(url=news_url, callback=self.parse)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
# content_time = response.xpath("""//*[@id="pubtime_baidu"]/text()""").extract()
public_time = re.search(
r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2}:\d{1,2})",
response.text).group(0)
except:
spiderUtil.log_level(8, response.url)
try:
contents = response.xpath(
"""//*[@id="articleBody"]/p/text()""").extract()
content = "".join(contents)
except:
spiderUtil.log_level(7, response.url)
source = "http://www.china.com.cn/"
try:
author_arr = response.xpath(
"""//*[@id="source_baidu"]//text()""").extract()
author = "".join(author_arr)
if author == '':
author = "中国网"
else:
author = author.split("来源：")[1].strip()
except:
spiderUtil.log_level(9, response.url)
try:
title_arr = response.xpath(
"/html/body/div/h1/text()").extract()
title = "".join(title_arr).strip()
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath(
"//div[@class='section-main']/p/text()").extract()
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
public_time = re.search(r"(\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2})",
response.text).group(0) + ":00"
public_time = response.url.split(
"/")[-3][:-2] + "-" + public_time
except:
# spiderUtil.log_level(8, response.url)
pass
try:
title_arr = response.xpath("//head/title//text()").extract()
title = "".join(title_arr).strip()
except:
spiderUtil.log_level(6, response.url)
try:
author_arr = response.xpath(
"//span[@id='copyfrom']//text()").extract()
author = "".join(author_arr).strip()
if author == "":
author = "中青在线"
except:
spiderUtil.log_level(9, response.url)
source = "http://www.cyol.com/"
try:
if content != "" and len(
content) >= 100 and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = re.search(
r"(\d{4}年\d{1,2}月\d{1,2}日\s\d{1,2}:\d{1,2})",
response.text).group(0).replace("年", "-").replace(
"月", "-").replace("日", "") + ":00"
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath(
"""/html/body/div/div/div/p/text()""").extract()
content = "".join(content_arr).strip()
except:
spiderUtil.log_level(7, response.url)
source = "http://www.southcn.com/"
try:
author_arr = response.xpath(
"""/html/body/div/div/div/div/span/i/a/text()""").extract(
)
author = "".join(author_arr).strip()
if author == "":
author = "央视网"
else:
author = author.replace("来源：", "")
except:
spiderUtil.log_level(9, response.url)
try:
title_arr = response.xpath(
"""/html/body/div/div/div/h1/text()""").extract()
title = "".join(title_arr).strip()
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = re.search(
r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2}:\d{1,2})",
response.text).group(0)
except:
# spiderUtil.log_level(8, response.url)
pass
try:
content_arr = response.xpath(
"""//div/div/div/div/div/p/text()""").extract()
content = "".join(content_arr).strip()
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
title_arr = response.xpath("//div/div/h2/text()").extract()
title = "".join(title_arr)
except:
spiderUtil.log_level(6, response.url)
try:
author_arr = response.xpath(
"""//*[@id="xl-headline"]/div/div/text()""").extract()
author = "".join(author_arr).strip()
if author == "":
author = "大众网"
else:
author = author.split("来源: ")[1].split("作者:")[0].strip()
except:
spiderUtil.log_level(9, response.url)
source = "http://www.dzwww.com/"
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = re.search(
r"(\d{4}年\d{1,2}月\d{1,2}日\s\d{1,2}:\d{1,2})",
response.text).group(0).replace("年", "-").replace(
"月", "-").replace("日", "") + ":00"
except:
# spiderUtil.log_level(8, response.url)
pass
try:
content_arr = response.xpath(
"//div[@class='left_zw']/p//text()").extract()
content = "".join(content_arr).strip()
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
title_arr = response.xpath(
"//div/div/div/div/h1//text()").extract()
title = "".join(title_arr)
except:
spiderUtil.log_level(6, response.url)
try:
author_arr = response.xpath(
"//div[@class='left-t']//text()").extract()
author = "".join(author_arr)
if author == "":
author = "中国新闻网"
except:
spiderUtil.log_level(9, response.url)
source = "http://www.chinanews.com/"
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_time = response.xpath(
"//main/section/section/div/span[4]/text()").extract()
public_time = str(str(content_time[0]) + ":00")
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath(
"/html/body/main/section/section/article/section/p/text()"
).extract()
content = "".join(content_arr)
except:
spiderUtil.log_level(7, response.url)
source = "http://www.rednet.cn/"
try:
author_arr = response.xpath(
"//main/section/section/div/span[1]/text()").extract()
author = "".join(author_arr).strip()
if author == "":
author = "红网"
else:
author = author.split("来源：")[1]
except:
spiderUtil.log_level(9, response.url)
try:
title_arr = response.xpath(
"//main/section/section/h1/text()").extract()
title = "".join(title_arr).strip()
except:
spiderUtil.log_level(6, response.url)
try:
# if content != "" and public_time.startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
print(item)
# yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_time = response.xpath(
"""//*[@id="main"]/div/div/div/div/div/span[1]/text()"""
).extract()
public_time = str(str(content_time[0]) + ":00")
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath(
"""//*[@id="article-content"]/p/text()""").extract()
content = "".join(content_arr)
except:
spiderUtil.log_level(7, response.url)
source = "http://www.71.cn/"
try:
author_arr = response.xpath(
"""//*[@id="main"]/div/div/div/div/div/span[2]/text()"""
).extract()
author = "".join(author_arr)
except:
spiderUtil.log_level(9, response.url)
try:
title = response.xpath(
"""//*[@id="main"]/div/div/div/div/h1/text()""").extract(
)[0]
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
# if content != "" :
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
print(content, public_time, title, author)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath("//div[@class='TRS_Editor']"
)[0].xpath('string(.)').extract()
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
author_arr = response.xpath(
"//meta[@name='author']/@content").extract()
if author_arr == []:
author = "中国青年网"
else:
author = author_arr[0]
except:
spiderUtil.log_level(9, response.url)
source = "http://www.youth.cn/"
try:
title = "".join(
response.xpath("//head/title/text()").extract()[0].split(
"_")[:-2]).strip()
except:
spiderUtil.log_level(6, response.url)
try:
public_time = re.search(
r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2}:\d{1,2})",
response.text).group(0)
except:
spiderUtil.log_level(8, response.url)
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_time = response.xpath(
"""//meta[@name="PubDate"]//@content""").extract()
# print(content_time)
# content_times = re.search(r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2})", content_time[0]).group(0)
# print(content_times)
public_time = str(content_time[0])
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath(
"""//div[@class="content"]//p//text()""").extract()
content = "".join(content_arr)
except:
spiderUtil.log_level(7, response.url)
source = "http://www.comnews.cn/"
try:
author = response.xpath(
"""//meta[@name="ContentSource"]//@content""").extract(
)[0].strip()
except:
spiderUtil.log_level(9, response.url)
try:
titles = response.xpath(
"""//meta[@name="ArticleTitle"]//@content""").extract()
title = "".join(titles)
except:
spiderUtil.log_level(6, response.url)
try:
# if content != "" and str(public_time).startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
print(item)
# yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = re.search(
r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2}:\d{1,2})",
response.text).group(0)
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath("//div[@class='left newstext']")[
0].xpath('string(.)').extract()[0]
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
author_list = [
"三湘风纪", "搜狐", "英国报姐", "我们爱历史", "最爱历史", "慢青年", "伟人勘察",
"大象公会", "中国历史文化网", "凤凰", "腾讯", "新浪", "解放日报", "参考消息", "新华网",
"红瞰天下", "海外网", "人民网", "中华读书报", "今日头条", "中国新闻网"
]
author = author_list[random.randint(0, len(author_list) - 1)]
except:
spiderUtil.log_level(9, response.url)
try:
title = response.xpath(
"//head/meta[@name='description']/@content").extract()[0]
except:
spiderUtil.log_level(6, response.url)
source = "http://www.xilu.com/"
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath(
"//div[@id='Content']//text()").extract()
content = "".join(content_arr).strip()
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
title_arr = response.xpath("//head/title//text()").extract()
title = "".join(title_arr).strip().strip()[:-8]
except:
spiderUtil.log_level(6, response.url)
try:
author = response.xpath(
"//head/meta[@name='author']/@content").extract()
if author == []:
author = "中国日报网"
else:
author = author[0]
except:
spiderUtil.log_level(9, response.url)
source = "http://www.chinadaily.com.cn/"
try:
public_time = re.search(
r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2})",
response.text).group(0) + ":00"
except:
# spiderUtil.log_level(8, response.url)
pass
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = re.search(r"(\d{4}-\d{1,2}-\d{1,2})",
response.text).group(0) + "00:00:00"
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath(
"//div[@class='TRS_Editor']/div/p//text()").extract()
content = "".join(content_arr).strip()
except:
spiderUtil.log_level(7, response.url)
source = "http://www.wenming.cn/"
try:
author_arr = response.xpath(
"//div[@class='box01']/div[@class='fl']/a//text()"
).extract()
author = "".join(author_arr).strip()
if author == "":
author = "文明网"
except:
spiderUtil.log_level(9, response.url)
try:
title_arr = response.xpath(
"//div[@id='title_tex']//text()").extract()
title = "".join(title_arr).strip()
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(
spiderUtil.get_yesterday_date()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = re.search(
r"(\d{4}-\d{1,2}-\d{1,2}T\d{1,2}:\d{1,2})",
response.text).group(0).replace("T", " ") + ":00"
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath("//div[@id='post_description']"
)[0].xpath('string(.)').extract()
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
title = response.xpath("//head/title/text()").extract()[0][:-3]
except:
spiderUtil.log_level(6, response.url)
try:
author_arr = response.xpath(
"//div[@id='post_author']/text()").extract()
author = "".join(author_arr)
if author == "":
author = "亿欧网"
except:
spiderUtil.log_level(9, response.url)
source = "https://www.iyiou.com/"
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_time = response.xpath(
"""//*[@id="pubtime_baidu"]/text()""").extract()
public_time = str(content_time[0])
except:
spiderUtil.log_level(8, response.url)
try:
contents = response.xpath(
"""//*[@id="allList"]/div/div/div/p/text()""").extract()
content = "".join(contents)
except:
spiderUtil.log_level(7, response.url)
source = "http://www.cankaoxiaoxi.com/"
try:
author = str(
response.xpath("""//*[@id="source_baidu"]/text()""").
extract()[0].strip()).replace("来源：", "")
except:
spiderUtil.log_level(9, response.url)
try:
title = response.xpath("//div/div/h1/text()").extract()[0]
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
# if content != "" :
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = response.xpath(
"//head/meta[@name='publishdate']/@content"
).extract()[0].replace("年", "-").replace("月", "-").replace(
"日", " ") + ":00"
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath("//div[@class='cl']")[0].xpath(
'string(.)').extract()
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
author = response.xpath("//head/meta[@name='source']/@content"
).extract()[0].split("-")[1]
except:
spiderUtil.log_level(9, response.url)
try:
title = response.xpath(
"//head/meta[@itemprop='name']/@content").extract()[0]
except:
spiderUtil.log_level(6, response.url)
source = "https://www.dahe.cn/"
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
# 标题解析
try:
title = response.xpath("//h1[@class='article-title']/text()"
).extract()[0].replace(
'\t',
'').replace('\n',
'').replace('\r', '')
except:
spiderUtil.log_level(6, response.url)
try:
public_time_tmp = response.xpath(
"//div[@class='article-infos']/span[@class='date']/text()"
).extract()[0]
if len(public_time_tmp) == 16:
public_time = public_time_tmp + ":00"
else:
public_time = public_time_tmp
except:
spiderUtil.log_level(8, response.url)
source = "http://www.stnn.cc/"
try:
content_arr = response.xpath(
"//div[@class='article-content fontSizeSmall BSHARE_POP']/p/text()"
).extract()
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.meta["url"]
item["title"] = title
item["author"] = "星岛环球网"
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = str(response.xpath("""//*[@id="pubtime_baidu"]/text()""").extract()[0].strip())+":00"
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath("""//*[@id="content"]/p/text()""").extract()
content = "".join(content_arr)
except:
spiderUtil.log_level(7, response.url)
source = "http://www.southcn.com/"
try:
author_arr = response.xpath("""//*[@id="source_baidu"]/text()""").extract()
author = "".join(author_arr).strip()
if author == "":
author = "澎湃新闻"
else:
author = author.replace("来源：","")
except:
spiderUtil.log_level(9, response.url)
try:
title_arr = response.xpath("""//*[@id="article_title"]/text()""").extract()
title = "".join(title_arr).strip()
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parsebody(self,response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
all_arr = response.xpath("""//script//text()""").extract()
data = "".join(all_arr).split("allData = ")[1].split("var adData")[0].strip()[:-1]
data = json.loads(data)
doc = data['docData']
try:
public_time = doc['newsTime']
except:
spiderUtil.log_level(8, response.url)
try:
content = doc['contentData']['contentList'][0]['data']
content = "".join(etree.HTML(content).xpath("//p//text()")).strip()
except:
spiderUtil.log_level(7, response.url)
source = "http://news.ifeng.com/"
try:
author = doc['source']
except:
spiderUtil.log_level(9, response.url)
try:
title = doc['title']
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["html_size"] = html_size
item["crawl_time"] = spiderUtil.get_time()
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath("//div[@id='main-content']")[
0].xpath('string(.)').extract()[0]
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
public_time = response.meta["public_time"]
except:
spiderUtil.log_level(8, response.url)
try:
author = response.xpath(
"//p[@class='fromInfo']/text()").extract()[0].split("：")[1]
except:
spiderUtil.log_level(9, response.url)
try:
title = response.xpath(
"//head/meta[@name='title']/@content").extract()[0]
except:
spiderUtil.log_level(6, response.url)
source = "http://www.wenweipo.com/"
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_time = response.xpath("""//*[@id="article"]/div/div/div/span/text()""").extract()
public_time = str(time.strftime('%Y', time.localtime(time.time()))) +"-"+ str(content_time[0]) + " " + str(content_time[1]) + ":00"
except:
# spiderUtil.log_level(8, response.url)
pass
try:
content_arr = response.xpath("""//*[@id="article"]/div/p/span/text()""").extract()
content = "".join(content_arr)
except:
spiderUtil.log_level(7, response.url)
source = "http://news.baidu.com/"
try:
author_arr = response.xpath("""//*[@id="article"]/div/div/p/text()""").extract()
author = "".join(author_arr)
except:
spiderUtil.log_level(9, response.url)
try:
title_arr = response.xpath("""//*[@id="article"]/div/h2/text()""").extract()
title = "".join(title_arr)
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parsebody(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = re.search(
r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2}:\d{1,2})",
response.text).group(0)
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath(
"//div[@id='endText']/p/text()").extract()
content = "".join(content_arr).strip()
except:
spiderUtil.log_level(7, response.url)
try:
author_arr = response.xpath(
"//a[@id='ne_article_source']//text()").extract()
author = "".join(author_arr).strip()
if author == "":
author = "网易新闻"
except:
spiderUtil.log_level(9, response.url)
source = "https://news.163.com/"
try:
if content != "" and public_time.startswith(
spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = response.meta["title"]
item["author"] = author
item["html_size"] = html_size
item["crawl_time"] = spiderUtil.get_time()
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath("//div[@id='articleText']//text()").extract()
content = "".join(content_arr).strip()
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
public_time = (re.search(r"(\d{4}年\d{1,2}月\d{1,2}日\s\d{1,2}:\d{1,2})", response.text).group(
0) + ":00").replace(
"年", "-").replace("月", "-").replace("日", "")
except:
spiderUtil.log_level(8, response.url)
source = "http://www.ce.cn/"
try:
title = response.xpath("//head/title/text()").extract()[0].split("_")[0]
except:
spiderUtil.log_level(6, response.url)
try:
author = response.xpath("//head/meta[@name='author']/@content").extract()[0]
except:
spiderUtil.log_level(9, response.url)
try:
if public_time.startswith(spiderUtil.get_first_hour()) and content != "":
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
public_time = re.search(r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2}:\d{1,2})", response.text).group(0)
except:
spiderUtil.log_level(8, response.url)
try:
content_arr = response.xpath("//div[@class='content']/p/text()").extract()
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
source = "http://www.bjnews.com.cn/"
try:
author = response.xpath("//span[@class='author']/text()").extract()[0].strip()
except:
spiderUtil.log_level(9, response.url)
try:
title = response.xpath("//div[@class='title']/h1/text()").extract()[0]
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and public_time.startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_time = response.xpath("""//div[@class="info"]//text()""").extract()
public_time = re.search(r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2}:\d{1,2})", content_time[0]).group(0)
except:
spiderUtil.log_level(8, response.url)
try:
content_arrs = response.xpath("""//td[@class="content"]//p//text()""").extract()
content_arr = content_arrs.split('推荐信息')[0]
content = "".join(content_arr)
except:
spiderUtil.log_level(7, response.url)
source = "http://www.188cf.net/"
try:
author = "188财富网"
except:
spiderUtil.log_level(9, response.url)
try:
title = response.xpath("""//h1//text()""").extract()[0]
except:
spiderUtil.log_level(6, response.url)
try:
if content != "" and str(public_time).startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# print(item)
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
def parse(self, response):
if response.status == 200:
text = response.text
html_size = sys.getsizeof(text)
try:
content_arr = response.xpath("//div[@class='post_text']/p/text()").extract()
content = "".join(content_arr)
# content = "".join(content_tmp.split())
except:
spiderUtil.log_level(7, response.url)
try:
author = response.xpath("//head/meta[@name='author']/@content").extract()[0]
except:
spiderUtil.log_level(9, response.url)
source = "http://www.e23.cn/"
try:
title = "".join(response.xpath("//head/title/text()").extract()[0].split("-")[:-2]).strip()
except:
spiderUtil.log_level(6, response.url)
try:
public_time = response.xpath("//div[@class='post_time']/p/text()").extract()[0]
except:
spiderUtil.log_level(8, response.url)
try:
if content != "" and public_time.startswith(spiderUtil.get_first_hour()):
item = NewsAllItem()
item["source"] = source
item["content"] = content
item["public_time"] = public_time
item["url"] = response.url
item["title"] = title
item["author"] = author
item["crawl_time"] = spiderUtil.get_time()
item["html_size"] = html_size
# 数据打入piplines处理
yield item
except:
pass
else:
spiderUtil.log_level(response.status, response.url)
