def parseAnimals(self, response):
html = HtmlParser(response)
if html.extract_urls('//div[@class="pagination"]/a[@class="next"]'):
for url in html.extract_urls('//div[@id="search_results"]/div/a'):
yield Request(url, callback="parseAnimal")
for url in html.extract_urls('//div[@class="pagination"]/a[@class="next"]'):
yield Request(url, callback="parseAnimals")
else:
for url in html.extract_urls('//div[@id="search_results"]/div/a'):
yield Request(url, callback="parseAnimal")
def parseAnimals(self,response):
html = HtmlParser(response)
if html.extract_urls('//div[@class="pagination"]/a[@class="next"]'):
for url in html.extract_urls('//div[@id="search_results"]/div/a'):
yield Request(url,callback="parseAnimal")
for url in html.extract_urls('//div[@class="pagination"]/a[@class="next"]'):
yield Request(url,callback="parseAnimals")
else:
for url in html.extract_urls('//div[@id="search_results"]/div/a'):
yield Request(url,callback="parseAnimal")
def parseCat(self, response):
parser = HtmlParser(response)
if 'Next' not in parser.xpath('//li/a/text()'):
for i in parser.xpath('//span[@class="bqQuoteLink"]/a//text()'):
self.mydb.quotes.insert({'quote': i})
else:
for i in parser.xpath('//span[@class="bqQuoteLink"]/a//text()'):
self.mydb.quotes.insert({'quote': i})
for url in parser.extract_urls('//li/a[contains(text(),"Next")]'):
yield Request(url, callback="parseCat")
def parseCat(self, response):
parser = HtmlParser(response)
if 'Next' not in parser.xpath('//li/a/text()'):
for i in parser.xpath('//span[@class="bqQuoteLink"]/a//text()'):
self.mydb.quotes.insert({'quote':i})
else:
for i in parser.xpath('//span[@class="bqQuoteLink"]/a//text()'):
self.mydb.quotes.insert({'quote':i})
for url in parser.extract_urls('//li/a[contains(text(),"Next")]'):
yield Request(url,callback="parseCat")
def parseCat(self, response):
parser = HtmlParser(response)
dbname= response.meta['u']
if not parser.xpath('//a[@class="next_page"]'):
for i in parser.xpath('//div[@class="quoteText"]'):
quote = i.text
for j in i.iterfind('a'):
author=j.text
self.mydb[dbname].insert({'quote':quote,'author':author})
else:
for i in parser.xpath('//div[@class="quoteText"]'):
quote = i.text
for j in i.iterfind('a'):
author=j.text
self.mydb[dbname].insert({'quote':quote,'author':author})
for url in parser.extract_urls('//a[@class="next_page"]'):
yield Request(url,callback="parseCat",meta={'u':dbname})
def parseCat(self, response):
parser = HtmlParser(response)
dbname = response.meta['u']
if not parser.xpath('//a[@class="next_page"]'):
for i in parser.xpath('//div[@class="quoteText"]'):
quote = i.text
for j in i.iterfind('a'):
author = j.text
self.mydb[dbname].insert({'quote': quote, 'author': author})
else:
for i in parser.xpath('//div[@class="quoteText"]'):
quote = i.text
for j in i.iterfind('a'):
author = j.text
self.mydb[dbname].insert({'quote': quote, 'author': author})
for url in parser.extract_urls('//a[@class="next_page"]'):
yield Request(url, callback="parseCat", meta={'u': dbname})
def parse(self, response):
parser = HtmlParser(response)
for i in parser.extract_urls(
'//div[@class="bqLn"]/div[@class="bqLn"]/a'):
yield Request(i, callback="parseCat")
def parse(self,response):
parser = HtmlParser(response)
for url in parser.extract_urls('//a[@class="actionLinkLite serif"]'):
dbname = url.split('/')[-1]
yield Request(url,callback="parseCat",meta={'u':dbname})
def parse(self, response):
parser = HtmlParser(response)
for url in parser.extract_urls('//a[@class="actionLinkLite serif"]'):
dbname = url.split('/')[-1]
yield Request(url, callback="parseCat", meta={'u': dbname})
def parse(self, response):
html = HtmlParser(response)
photo_list = ['//li[@class="first"]', '//li[@class=" "]', '//li[@class="last"]']
for item in photo_list:
for url in html.extract_urls(item):
yield Request(url, callback="parseAnimals")
def parse(self, response):
parser = HtmlParser(response)
for i in parser.extract_urls('//div[@class="bqLn"]/div[@class="bqLn"]/a'):
yield Request(i,callback="parseCat")
def parse(self,response):
html = HtmlParser(response)
photo_list = ['//li[@class="first"]','//li[@class=" "]','//li[@class="last"]']
for item in photo_list:
for url in html.extract_urls(item):
yield Request(url,callback="parseAnimals")