复制代码 代码如下:
from selenium import selenium
class MySpider(CrawlSpider):
name = 'cnbeta'
allowed_domains = ['cnbeta.com']
start_urls = ['https://www.jb51.net']
rules = (
# Extract links matching 'category.php' (but not matching 'subsection.php')
# and follow links from them (since no callback means follow=True by default).
Rule(SgmlLinkExtractor(allow=('/articles/.*\.htm', )),
callback='parse_page', follow=True),
# Extract links matching 'item.php' and parse them with the spider's method parse_item
)
def __init__(self):
CrawlSpider.__init__(self)
self.verificationErrors = []
self.selenium = selenium("localhost", 4444, "*firefox", "https://www.jb51.net")
self.selenium.start()
def __del__(self):
self.selenium.stop()
print self.verificationErrors
CrawlSpider.__del__(self)
def parse_page(self, response):
self.log('Hi, this is an item page! %s' % response.url)
sel = Selector(response)
from webproxy.items import WebproxyItem
sel = self.selenium
sel.open(response.url)
sel.wait_for_page_to_load("30000")
import time
time.sleep(2.5)
解析js
更新日志
- 孙悦.1996-伙伴【正大国际】【WAV+CUE】
- 纪钧瀚《钢琴阅读时光 雨中书店聆听轻音乐》[FLAC/分轨][399.62MB]
- 证声音乐图书馆《走向自然 疗心爵士乐》[320K/MP3][87.4MB]
- 证声音乐图书馆《走向自然 疗心爵士乐》[FLAC/分轨][184.94MB]
- 陈慧娴.2018-Priscilla-Ism演唱会3CD(2024环球红馆40复刻系列)【环球】【WAV+CUE】
- 郑秀文.1999-我应该得到(国)【华纳】【WAV+CUE】
- 陈家慧.2011-钢琴酒吧2CD【龙吟唱片】【WAV+CUE】
- 证声音乐图书馆《雨季 蓝调吉他 Rainy Blues》[320K/MP3][45.01MB]
- 证声音乐图书馆《雨季 蓝调吉他 Rainy Blues》[FLAC/分轨][109.13MB]
- 赞多《序章》[320K/MP3][45.54MB]
- 许巍.2004-每一刻都是崭新的【步升大风】【WAV+CUE】
- 群星.2024-四方馆影视原声带【韶愔音乐】【FLAC分轨】
- 陈雷.1997-安锁咧【金圆唱片】【WAV+CUE】
- 关淑怡.2013-MY.FAVORITE.SK.3CD【环球】【WAV+CUE】
- Sweety.2006-花言乔语【丰华】【WAV+CUE】