Scrapy爬取世纪佳缘 --post请求

• scrapy默认的是get请求，当网页是post请求的时候需要重写start_requests方法，重构起始url请求需要浏览器--参数的数据请求

# windoms运行的时候如果出现了以下错误：
"""UnicodeEncodeError: 'gbk' codec can't encode character '\u2764' in position 261: illegal multibyte sequence"""
# 是由于windows标准输出的默认编码（gbk）无法识别编码格式，解决方法：
# 改变标准输出的默认编码 
import sys,io
sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')
# 可以把字符串变成xpath格式的标签
from scrapy.selector import Selector
# 移除文本中的标签
from w3lib.html import remove_tags
class SjjySpider(scrapy.Spider):
    name = 'sjjy'
    allowed_domains = ['jiayuan.com']
    start_urls = ['http://search.jiayuan.com/v2/search_v2.php']

    def start_requests(self):
        form_data = {
            'sex': 'f',
            'key': '',
            'stc': '1: 11, 2: 20.28, 23: 1',
            'sn': 'default',
            'sv': '1',
            'p': '2',
            'f': 'search',
            'listStyle': 'bigPhoto',
            'pri_uid': '0',
            'jsversion': 'v5'
        }
        # formdata:对应的表单数据
        for url in self.start_urls:
            yield scrapy.FormRequest(
                url,
                formdata=form_data,
                meta={'form_data': form_data}
                , dont_filter=True)

    def parse(self, response):
        # print(response.status)
        print(response.text)
        # 匹配json，转化成字典
        pattern = re.compile('##jiayser##(.*?)##jiayser##', re.S)
        result = re.findall(pattern, response.text)[0]
        data = json.loads(result)
        for userinfo in data['userInfo']:
            # print(userinfo)
            item = ShijijiayuanItem()
            # uid
            item['uid'] = userinfo['uid']
            # 头像
            item['header_img'] = userinfo['image']
            # 性别
            item['sex'] = userinfo['sex']

            # remove_tags移出标签
            item['randTag'] = remove_tags(userinfo['randTag'])
            # 年龄
            item['age'] = userinfo['age']
            #  身高
            item['height'] = userinfo['height']
            # 个性签名
            item['shortnote'] = userinfo['shortnote']
            # 工作地点
            item['workAddress'] = userinfo['work_location']
            # 对另一半要求
            item['mathCtion'] = userinfo['matchCondition']
            # 匿名名
            item['nickname'] = userinfo['nickname']
            print(item)
            yield item
        # 发起下一页
        form_data = response.meta['form_data']
        # print(from_data)
        cur_page = form_data['p']
        next_page = int(cur_page) + 1
        pageTotal = int(data['pageTotal'])
        if next_page < pageTotal:
            form_data['p'] = str(next_page)
            print(cur_page)

            yield scrapy.FormRequest('http://search.jiayuan.com/v2/search_v2.php',formdata=form_data,meta={'form_data': form_data},callback=self.parse)