九色国产,午夜在线视频,新黄色网址,九九色综合,天天做夜夜做久久做狠狠,天天躁夜夜躁狠狠躁2021a,久久不卡一区二区三区

程序目的：

根據(jù)特定的SNP list， 在千人基因組數(shù)據(jù)庫中爬取CHB人群的等位基因頻率信息，如https://www.ncbi.nlm.nih.gov/variation/tools/1000genomes/?q=rs12340895。
因為網(wǎng)頁是動態(tài)的數(shù)據(jù)，嵌入了JavaScript代碼，因此借助selenium來爬取信息。
Beautiful Soup是Python的一個庫，最主要的功能是從網(wǎng)頁抓取數(shù)據(jù)。Beautiful Soup提供一些簡單的、python式的函數(shù)用來處理導航、搜索、修改分析樹等功能。它是一個工具箱，通過解析文檔為用戶提供需要抓取的數(shù)據(jù)，避免了用繁雜的正則表達式。

準備工作：

• 0、安裝selenium：pip install -U selenium

• 1、安裝chromedriver: brew install chromedriver

  注意：使用該命令安裝的時候可能安裝的chromedriver不是最新版，有可能導致與chrome瀏覽器版本不兼容而報如下錯誤：
  unknown error: Runtime.executionContextCreated has invalid ‘context’: {“auxData”:{“frameId”:”11740.1”,”isDefault”:true},”id”:1,”name”:”“,”origin”:”://”}
  (Session info: chrome=54.0.2840.71)
  (Driver info: chromedriver=2.9.248307,platform=Mac OS X 10.9.4 x86_64)
  這個其實是老版本的chromedriver 無法正常啟動chrome。解決辦法就是下載最新的chromedriver.
  如果用brew upgrade命名更新不了chromedriver，要去https://sites.google.com/a/chromium.org/chromedriver/downloads 下載剛發(fā)布的Latest Release: ChromeDriver 2.25

• 2、下載完畢chromedriver，Move the file to /usr/bin directory sudo mv chromedriver /usr/bin

• 3、更改chromedriver權限，Go to /usr/bin directory and you would need to run something like chmod a+x chromedriver to mark it executable.

源代碼

# -*- coding:utf-8 -*-from bs4 import BeautifulSoupimport timefrom selenium import webdriverfrom selenium.common.exceptions import NoSuchElementExceptiondef get_allele_feq(browser, snp):    browser.get(    'https://www.ncbi.nlm.nih.gov/variation/tools/1000genomes/?q=%s' %snp) #Load page    # browser.implicitly_wait(60) #智能等待xx秒    time.sleep(30) #加載時間較長，等待加載完畢    # browser.find_element_by_css_selector("div[title=\"Han Chinese in Bejing, China\"]") #use selenium function to find elements    # 把selenium的webdriver調用page_source函數(shù)在傳入BeautifulSoup中，就可以用BeautifulSoup解析網(wǎng)頁了    bs = BeautifulSoup(browser.page_source, "lxml")    # bs.find_all("div", title="Han Chinese in Bejing, China")    try:        race = bs.find(string="CHB")        race_data = race.find_parent("div").find_parent(            "div").find_next_sibling("div")        # print race_data        race_feq = race_data.find("span", class_="gt-selected").find_all("li") # class_ 防止Python中類關鍵字重復，產生語法錯誤        base1_feq = race_feq[0].text  #獲取標簽的內容        base2_feq = race_feq[1].text        return snp, base1_feq, base2_feq  # T=0.1408 C=0.8592    except NoSuchElementException:        return "%s:can't find element" %snp def main():    browser = webdriver.Chrome() # Get local session of chrome    fh = open("./4diseases_snps_1kCHB_allele_feq.list2", 'w')    snps = open("./4diseases_snps.list.uniq2",'r')    for line in snps:        snp = line.strip()        response = get_allele_feq(browser, snp)        time.sleep(1)        fh.write("\t".join(response)) #unicode 編碼的對象寫到文件中后相當于print效果        fh.write("\n")        print "\t".join(response)        time.sleep(1)  # sleep a few seconds    fh.close()    browser.quit()  # 退出并關閉窗口的每一個相關的驅動程序if __name__ == '__main__':    main()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49

參考資料：

1]: http://beautifulsoup.readthedocs.io/zh_CN/latest/ #Beautiful Soup 4.4.0 文檔
2]: http://blog.csdn.net/buptlrw/article/details/48828201
3]: http://www.cnblogs.com/duyang/p/5144987.html
4]: http://blog.csdn.net/cjsafty/article/details/9206323
5]: http://stackoverflow.com/questions/8255929/running-webdriver-chrome-with-selenium
6]: https://pypi.python.org/pypi/selenium#downloads
7]: http://blog.csdn.net/leejeff/article/details/52935706