def get_api_url(api_url, api_key, target, **filters):
'''Build the API URL to query a list of proxies'''
api_url = urljoin(api_url, API_ENDPOINT)
api_url = urljoin(api_url + '/', target)
api_url = add_or_replace_parameter(api_url, 'api_key', api_key)
for f_key, f_val in filters.items():
api_url = add_or_replace_parameter(api_url, f_key, f_val)
return api_url
def __init__(self,
place=None,
start=1,
count=None,
expiry=None,
*args,
**kwargs):
super(ZapSpider, self).__init__(*args, **kwargs)
self.start = int(start) if start else 1
self.count = int(count) if count else None
self.expiry = self.parse_timedelta(expiry)
self.crawl_count = 0
self.scrape_count = 0
self.total_crawl = 0
self.total_scrape = 0
self.link_extractor = LinkExtractor(
restrict_xpaths=
'//div[@id="list"]//a[contains(@class, "detalhes")]',
deny='/lancamento/',
unique=True,
process_value=url_query_cleaner)
self.start_urls = [
urljoin('https://www.zapimoveis.com.br/venda/imoveis/',
place or 'pe+recife' if place != 'all' else ''),
]
self.lua_script = """
def start_requests(self):
with open("quotesdb.jl") as f:
for line in f:
quote = json.loads(line)
yield scrapy.Request(
urljoin('http://www.goodreads.com',
quote.get('author', {}).get('goodreads_link')))
def deal_img(img_urls_raw):
img_urls_end = []
if not isinstance(img_urls_raw, type([])):
img_urls_raw = [img_urls_raw]
for img_url_raw in img_urls_raw:
if 'http' or 'www' in img_url:
img_url = urljoin('https://www.atc.org.au/', img_url_raw)
img_urls_end.append(img_url)
return img_urls_end
def get_index(contentqueue):
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36',
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'
}
urls=['http://bts.gov.cn/xw/gjgn/']#国内
url2=['http://bts.gov.cn/xw/zdxw/']#师事
url3=['http://www.bts.gov.cn/zcms/']#部门动态
url4=['http://bts.gov.cn/xw/zsjg/']#直属单位
url5=['http://bts.gov.cn/xw/gjgn/']
url6=['http://bts.gov.cn/xw/qt/']#其它
url7=['http://www.bts.gov.cn/gk/tzgg/']#通知公告
url9=['http://www.bts.gov.cn/gk/rsxx/']#人事信息
url10=['http://www.bts.gov.cn/gk/ywgz/']#业务工作
url11=['http://www.bts.gov.cn/gk/wjzc/']#文件政策
url12=['http://www.bts.gov.cn/gk/zcjd1/']#政策解读
url13=['http://www.bts.gov.cn/gk/tjxx/']#统计信息
urls_all=urls+url2+url3+url4+url5+url6+url7+url9+url10+url11+url12+url13
for one_url in urls_all:
response1=get_response_and_text(url=one_url,headers=headers,charset='utf-8')
response_in_fucntion=response1['response_in_function']
if not response_in_fucntion:
continue
response_in_fucntion_text=response1['response_in_function_text']
datasoup=BeautifulSoup(response_in_fucntion_text,'lxml')
try:
for one_li in datasoup.select(
'body > div.mainBg > div.listMain.pageWidth.clearself > div.ListRightContent.clearself > div.docuContent.listul > ul > li'):
# print one_li.text
url_raw = one_li.select('a')[0].get('href')
title = one_li.select('a')[0].text.strip()
url_end = urljoin(basic_url, url_raw)
id=url_end.split('/')[-1].split('.')[0]
if 'bts.gov.cn' in url_end:
print url_end
print title
# print one_li.select('a')[1].text#publish_time//2017-04-04
index_dict={
'title':title,
'url':url_end,
'id':id,
'spider_time':datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
'parent_id':id,
}
contentqueue.put(index_dict)
except Exception as e:
print e
print one_url
def deal_img_urls(img_urls_raw):
img_url_list = []
for one_img_url in img_urls_raw:
if 'paypal_cn' or 'pixel.gif' in one_img_url:
continue
if 'http' and 'www' not in one_img_url:
url_img = urljoin('http://www.tibetanyouthcongress.org/',
one_img_url)
img_url_list.append(url_img)
return img_url_list
def deal_img_urls(img_urls_raw):
img_urls_dealed = []
for one_url in img_urls_raw:
if 'download-pdf' in one_url:
continue
if 'http' not in one_url:
one_url_dealed = urljoin('http://www.savetibet.org/',
one_url)
img_urls_dealed.append(one_url_dealed)
return img_urls_dealed
def get_content(data, comment_queue):
Re_find_img = re.compile(r'src\=\"(.*?)\"')
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36',
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'
}
basic_url = 'http://www.altxw.com/news/content/'
url = data['url']
response1 = get_response_and_text(url=url,
headers=headers,
charset='utf-8')
response_in_function = response1['response_in_function']
if not response_in_function:
return
try:
response_in_function_text = response1['response_in_function_text']
datasoup = BeautifulSoup(response_in_function_text, 'lxml')
# title=datasoup.select('body > div.body > div > div.main.l > div > div > h1')[0].text()
source = datasoup.select(
'body > div.body > div > div.main.l > div > div > div > li:nth-of-type(2)'
)[0].text.split(u'：')[1]
content = ''
for i in datasoup.select(
'body > div.body > div > div.main.l > div > div > ul > p'):
content += i.text
content_div = datasoup.select('div > div.main.l > div > div > ul')[0]
img_urls = Re_find_img.findall(str(content_div))
img_urls2 = []
for one_img_url in img_urls:
one_img_url = urljoin(basic_url, one_img_url.strip('../'))
img_urls2.append(one_img_url)
print img_urls2
data['source'] = source
data['content'] = content
data['img_urls'] = img_urls2
comment_queue.put(data)
except Exception as e:
print e
def _execute(self):
"""
Parse with the first successful option
"""
if not self.items:
for option in self.template.items:
output = self._extract(self.response, option)
self.items.extend(output)
if self.items:
break
if not self.links:
for option in self.template.links:
suffix = option.get('suffix')
callback = option['callback']
priority = option.get('priority', 0)
for link in self._extract(self.response, option):
link = dict(**link)
link.setdefault('callback', callback)
link.setdefault('priority', priority)
suffix = link.pop('suffix', '') or suffix
if suffix:
link['url'] = urljoin(link['url'], suffix)
self.links.append(link)
def get_content(data, result_queue):
url = data['url']
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36',
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'
}
basic_url = 'http://bts.gov.cn/'
Re_sub_javascript2 = re.compile(r'<script[\S|\s]*?>[\s|\S]*?<\/script\>')
Re_find_time = re.compile(r'(\d{4}\-\d{2}\-\d{2} \d{2}\:\d{2}\:\d{2})')
Re_find_img = re.compile(r'src\=\"(.*?)\"')
Re_find_cource = re.compile(ur'来源：(.*?) ')
try:
response1 = get_response_and_text(url=url,
headers=headers,
charset='utf-8')
response_in_function = response1['response_in_function']
if not response_in_function:
return
response_in_function_text = response1['response_in_function_text']
response_in_function_text_dealed = Re_sub_javascript2.sub(
'', response_in_function_text)
datasoup = BeautifulSoup(response_in_function_text_dealed, 'lxml')
title = datasoup.select(
'body > div > div.detailMain.pageWidth > div.pargraph > h1'
)[0].text
content = ''
for i in datasoup.select(
'body > div > div.detailMain.pageWidth > div.pargraph div.detailPar p'
):
content += i.text
# print content
source = Re_find_cource.findall(response_in_function_text_dealed)
if source:
source = source[0]
else:
source = ''
content_str = datasoup.select(
'body > div.mainBg > div.detailMain.pageWidth > div.pargraph > div.detailPar'
)[0]
content_str2 = str(content_str)
img_urls = Re_find_img.findall(content_str2)
img_urls2 = []
for one_img_url in img_urls:
img_url_dealed = urljoin(basic_url, one_img_url)
img_urls2.append(img_url_dealed)
publish_div = datasoup.select(
'body > div > div.detailMain.pageWidth > div.pargraph > h6'
)[0].text
publish_time = Re_find_time.findall(publish_div)[0]
data['content'] = content
data['publish_time'] = publish_time
data['img_urls'] = img_urls2
data['source'] = source
data['publish_user'] = ''
pass
result_queue.put(data)
except Exception as e:
print e
url13 = ['http://www.bts.gov.cn/gk/tjxx/'] # 统计信息
urls_all = urls + url2 + url3 + url4 + url5 + url6 + url7 + url9 + url10 + url11 + url12 + url13
basic_url = 'http://bts.gov.cn/'
for oneurl in url7:
response = requests.get(url=oneurl, headers=headers)
response.encoding = 'utf-8'
datasoup = BeautifulSoup(response.text, 'lxml')
# try:
# print datasoup.select('body > div.mainBg > div.detailMain.pageWidth > div.pargraph > h1')
# except Exception as e:
# print oneurl
try:
for one_li in datasoup.select(
'body > div.mainBg > div.listMain.pageWidth.clearself > div.ListRightContent.clearself > div.docuContent.listul > ul > li'
):
# print one_li.text
url_raw = one_li.select('a')[0].get('href')
title = one_li.select('a')[0].text
url_end = urljoin(basic_url, url_raw)
if 'bts.gov.cn' in url_end:
print url_end
print title
print one_li.select('a')[1].text
except Exception as e:
print e
print oneurl
response_text=response1.text
basic_url='http://bts.gov.cn/'
content1=Re_sub_javascript2.sub('',response1.text)
datasoup=BeautifulSoup(content1,'lxml')
print datasoup.select('body > div > div.detailMain.pageWidth > div.pargraph > h1')[0].text
content=''
for i in datasoup.select('body > div > div.detailMain.pageWidth > div.pargraph div.detailPar p'):
content+= i.text
source=Re_find_cource.findall(response_text)
print source[0]
content_str=datasoup.select('body > div.mainBg > div.detailMain.pageWidth > div.pargraph > div.detailPar')[0]
content_str2=str(content_str)
img_urls=Re_find_img.findall(content_str2)
print img_urls
img_urls2=[]
for one_img_url in img_urls:
img_url_dealed=urljoin(basic_url,one_img_url)
img_urls2.append(img_url_dealed)
print img_urls2
print content
publish_div= datasoup.select('body > div > div.detailMain.pageWidth > div.pargraph > h6')[0].text
print Re_find_time.findall(publish_div)[0]
def deal_img_urls(img_urls):
img_result = []
for one_img in img_urls:
img_urls = urljoin('http://www.tibetswiss.ch/', one_img)
img_result.append(img_urls)
return img_result
