本文整理汇总了Python中scrapy.http.request.Request.meta['gender']方法的典型用法代码示例。如果您正苦于以下问题:Python Request.meta['gender']方法的具体用法?Python Request.meta['gender']怎么用?Python Request.meta['gender']使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类scrapy.http.request.Request
的用法示例。
在下文中一共展示了Request.meta['gender']方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: parse_listing
# 需要导入模块: from scrapy.http.request import Request [as 别名]
# 或者: from scrapy.http.request.Request import meta['gender'] [as 别名]
def parse_listing(self,response):
url = "http://therapists.psychologytoday.com/"
gender = response.meta['gender']
results = response.xpath('//div[@class="result-name"]//@href').extract()
if self.randomRun:
profiles = response.meta['profiles']
results = sample(results,min(profiles,len(results)))
if not response.xpath('//div[@class="NoMatchingFound"]').extract():
for res in results:
request = Request(url+res,callback=self.parse_item)
request.meta['gender'] = gender
if(self.profilesScraped<self.profilesMax):
yield request
if not self.randomRun:
for x in response.xpath("//div[@class='endresults-right']//a[@title='More Therapists' and not(contains(@class,'here'))]//@href").extract():
request = Request(url+x,callback=self.parse_listing)
request.meta['gender'] = gender
yield request
示例2: parse
# 需要导入模块: from scrapy.http.request import Request [as 别名]
# 或者: from scrapy.http.request.Request import meta['gender'] [as 别名]
def parse(self,response):
states = response.xpath("//div[@class='row listItems'][1]//@href").extract()
if self.randomRun:
while self.profilesScraped < self.profilesMax:
stateRand = randint(0,len(states)-1)
startOffset = (randint(0,self.maxOffset/20)*20)+1
gender = randint(1,2)
url = "http://therapists.psychologytoday.com/rms/"+states[stateRand]+'?therapist_gender='+str(gender)+'&rec_next='+str(startOffset)
request = Request(url,callback=self.parse_listing)
request.meta['profiles'] = randint(1,5)
request.meta['gender'] = gender
yield request
else:
for state in states:
url = "http://therapists.psychologytoday.com/rms/"+state+'?therapist_gender=1'
request = Request(url,callback=self.parse_listing)
request.meta['gender'] = 1
yield request
url = "http://therapists.psychologytoday.com/rms/"+state+'?therapist_gender=2'
request = Request(url,callback=self.parse_listing)
request.meta['gender'] = 2
yield request