def parse_url(url="http://www.highya.com/"):
page = req_main(url)
if page:
soup = BeautifulSoup(page)
latest_reviews_h3 = soup.find("h3", text=re.compile("latest reviews:"))
if latest_reviews_h3:
post_div = latest_reviews_h3.find_next("div", attrs={"class":"clearfix like-right-col"})
if post_div:
all_li = post_div.find_all("li")
all_a = [li.find("a") for li in all_li]
for a in all_a:
link = "http://www.highya.com%s" % a.get("href")
page2 = req_main(url)
if page2:
soup2 = BeautifulSoup(page2)
article_tag = soup2.find("article", attrs={"class":"product-article"})
if article_div:
header = article_tag.find("header")
domain = "www.highya.com"
main_title = soup2.find("title").text()
main_title_link = link
article_div = article_tag.find("div", attrs={"class":"site-section section-article"})
blog_title = article_div.find("h2").text()
blog_link = link
itemtype = header.get("itemtype").split("/")[-1]
category = itemtype
cat_link = link
entry_content = article_div
entry_text = article_div.text()
def home_page_link(self):
self.creat_avv_blog_scrap_table()
# r = self.req_proxy()
# page = r.content
# r.close()
link_list = [
"http://testolimitfacts.com/",
# "http://testolimitfacts.com/testo-limit-review/",
# "http://testolimitfacts.com/testo-limit-review/",
# "http://testolimitfacts.com/slimgenix-pro/",
# "http://testolimitfacts.com/power-pro/",
# "http://testolimitfacts.com/addium-brain-enhancer-another-scam/",
# "http://testolimitfacts.com/enduros-male-enhancement/",
# "http://testolimitfacts.com/testo-xl/",
# "http://testolimitfacts.com/is-spartagen-xt-scam/",
# "http://testolimitfacts.com/elite-test-360/",
# "http://testolimitfacts.com/honest-green-coffee-bean-extract/",
# "http://testolimitfacts.com/premium-natural-garcinia-cambogia/",
# "http://testolimitfacts.com/maximum-shred/",
# "http://testolimitfacts.com/extreme-home-profits-review-worth-the-money-or-a-scam/",
# "http://testolimitfacts.com/30-day-change/",
# "http://testolimitfacts.com/100-day-loans/",
]
for link in link_list:
# page = main_req(link)
page = req_main(link)
if page:
self.get_link_from_first_page(link, page)
def home_page_link(self):
self.creat_avv_blog_scrap_table()
# r = self.req_proxy()
# page = r.content
# r.close()
link_list = ["http://www.healthyminimarket.com",
# "http://www.healthyminimarket.com/page/2/",
# "http://www.healthyminimarket.com/page/3/",
# "http://www.healthyminimarket.com/page/4/",
# "http://www.healthyminimarket.com/page/5/",
# "http://www.healthyminimarket.com/page/6/",
# "http://www.healthyminimarket.com/page/7/",
# "http://www.healthyminimarket.com/page/8/",
# "http://www.healthyminimarket.com/page/9/",
# "http://www.healthyminimarket.com/page/10/",
# "http://www.healthyminimarket.com/page/11/",
# "http://www.healthyminimarket.com/page/12/",
# "http://www.healthyminimarket.com/page/13/",
# "http://www.healthyminimarket.com/page/15/",
# "http://www.healthyminimarket.com/page/16/"
]
for link in link_list:
# page = main_req(link)
page = req_main(link)
if page:
self.get_link_from_first_page(page)
def open_home_page(self):
self.creat_avv_blog_scrap_table()
# r = self.req_proxy()
# page = r.content
# r.close()
link = "http://www.healthcaresdiscussion.com"
#page = main_req(link)
page = req_main(link)
if page:
link_to_extract = self.get_all_link_home_page(page)
map(self.get_page_next_link, link_to_extract)
def get_page_next_link(self, link):
sql = """SELECT * FROM avv_blog_scrap_table WHERE blog_link = '%s' """ % (self.my_strip(link))
self.cursor.execute(sql)
results = self.cursor.fetchall()
if not results:
# r2 = self.req_proxy(link=link)
# page2 = r2.content
# r2.close()
#page2 = main_req(link)
page2 = req_main(link)
if page2:
self.get_detail_next_page(link, page2)
def prev_home_page(self):
self.creat_avv_blog_scrap_table()
link_lists = ['http://www.healthcaresdiscussion.com/page/2/',
'http://www.healthcaresdiscussion.com/page/3/']
for link in link_lists:
# r = self.req_proxy(link=link)
# page = r.content
# r.close()
page = req_main(link)
if page:
link_to_extract = self.get_all_link_home_page(page)
map(self.get_page_next_link, link_to_extract)
