def crawler():
driver = Chrome(cache_path=r"E:\Temp")
# 采集城市编码列表
spider_city_code = SpiderCityCode(driver)
result1 = spider_city_code.run()
Utils.io.write_json("anjuke_city_code.json", result1)
# 采集城市房源数量
city_code_list = Utils.io.load_json("anjuke_city_code.json")
city_info_list = Utils.io.load_json("anjuke_city_infor.json", default={})
spider_city_info = SpiderCityInfo(driver)
for city_name, city_code in city_code_list.items():
if city_name not in city_info_list:
city_info_list[city_name] = spider_city_info.run(city_code=city_code)
Utils.io.write_json("anjuke_city_info.json", city_info_list)
time.sleep(2)
driver.quit()
import crawlertool as tool
from Selenium4R import Chrome
class SpiderAnjukeCityCodeList(tool.abc.SingleSpider):
"""
安居客城市编码列表爬虫
"""
def __init__(self, driver):
self.driver = driver
def running(self) -> List[Dict]:
self.driver.get("https://www.anjuke.com/sy-city.html")
result = []
for city_label in self.driver.find_elements_by_css_selector(
"body > div.content > div > div.letter_city > ul > li > div > a"
):
city_name = city_label.text
city_code = city_label.get_attribute("href").replace(
"https://", "").replace(".anjuke.com/", "")
result.append({"city_name": city_name, "city_code": city_code})
return result
if __name__ == "__main__":
driver = Chrome(cache_path=r"E:\Temp")
print(SpiderAnjukeCityCodeList(driver).running())
driver.quit()
