ssl._create_default_https_context = ssl._create_unverified_context
img_json_folder = 'json_dir'
def average_split_task(task_list, each_task_count):
return [task_list[i:i+each_task_count] for i in range(len(task_list)) if i%each_task_count==0]
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_5_8) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.696.68 Safari/534.24",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_4) AppleWebKit/534.30 (KHTML, like Gecko) Chrome/12.0.742.100 Safari/534.30",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_6) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.696.12 Safari/534.24",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_6) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.698.0 Safari/534.24",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_7) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.696.68 Safari/534.24",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.696.0 Safari/534.24",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_4; en-gb) AppleWebKit/528.4+ (KHTML, like Gecko) Version/4.0dp1 Safari/526.11.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_4; en-us) AppleWebKit/528.4+ (KHTML, like Gecko) Version/4.0dp1 Safari/526.11.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/ Safari/530.5",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; en-US) AppleWebKit/530.6 (KHTML, like Gecko) Chrome/ Safari/530.6",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; en-US) AppleWebKit/530.9 (KHTML, like Gecko) Chrome/ Safari/530.9",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.99 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; en-gb) AppleWebKit/528.10+ (KHTML, like Gecko) Version/4.0dp1 Safari/526.11.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_7; en-US) AppleWebKit/531.3 (KHTML, like Gecko) Chrome/3.0.192 Safari/531.3",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_7; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.196 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_7; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.198 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_7; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_7; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.212.1 Safari/532.1",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_7; en-us) AppleWebKit/530.19.2 (KHTML, like Gecko) Version/4.0.1 Safari/530.18",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_7; en-us) AppleWebKit/530.19.2 (KHTML, like Gecko) Version/4.0.2 Safari/530.19",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_7; en-us) AppleWebKit/531.2+ (KHTML, like Gecko) Version/4.0.1 Safari/530.18",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.197 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.198 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.203.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.207.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.208.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.210.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.2 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.221.8 Safari/532.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.5 Safari/532.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.8 (KHTML, like Gecko) Chrome/4.0.302.2 Safari/532.8",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.343.0 Safari/533.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/534.1 (KHTML, like Gecko) Chrome/6.0.422.0 Safari/534.1",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/8.0.552.224 Safari/534.10",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.127 Safari/534.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/534.2 (KHTML, like Gecko) Chrome/6.0.453.1 Safari/534.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-us) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.3 Safari/531.21.10",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; es-es) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; fi-fi) AppleWebKit/531.9 (KHTML, like Gecko) Version/4.0.3 Safari/531.9",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; fr-fr) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; it-it) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; ja-jp) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; nl-nl) AppleWebKit/531.22.7 (KHTML, like Gecko) Version/4.0.5 Safari/531.22.7",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; zh-cn) AppleWebKit/533.18.1 (KHTML, like Gecko) Version/5.0.2 Safari/533.18.5",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; zh-tw) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.203.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.203.4 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.204.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.206.1 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.212.1 Safari/532.1",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.307.11 Safari/532.9",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.86 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_0; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.99 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.207.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.209.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.2 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.212.0 Safari/532.0",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.221.8 Safari/532.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.4 Safari/532.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.86 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.472.63 Safari/534.3",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_1; nl-nl) AppleWebKit/532.3+ (KHTML, like Gecko) Version/4.0.3 Safari/531.9",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; de-at) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; en-US) AppleWebKit/530.6 (KHTML, like Gecko) Chrome/2.0.174.0 Safari/530.6",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.343.0 Safari/533.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.366.0 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.70 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.99 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; ja-jp) AppleWebKit/531.22.7 (KHTML, like Gecko) Version/4.0.5 Safari/531.22.7",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; ru-ru) AppleWebKit/533.2+ (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; ca-es) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; de-de) AppleWebKit/531.22.7 (KHTML, like Gecko) Version/4.0.5 Safari/531.22.7",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; el-gr) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-US) AppleWebKit/533.3 (KHTML, like Gecko) Chrome/5.0.363.0 Safari/533.3",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.366.0 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-US) AppleWebKit/534.1 (KHTML, like Gecko) Chrome/6.0.428.0 Safari/534.1",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-US) AppleWebKit/534.2 (KHTML, like Gecko) Chrome/6.0.453.1 Safari/534.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.456.0 Safari/534.3",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-au) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-us) AppleWebKit/531.21.11 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-us) AppleWebKit/531.22.7 (KHTML, like Gecko) Version/4.0.5 Safari/531.22.7",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-us) AppleWebKit/533.4+ (KHTML, like Gecko) Version/4.0.5 Safari/531.22.7",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-us) AppleWebKit/534.1+ (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; it-it) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; ja-jp) AppleWebKit/531.22.7 (KHTML, like Gecko) Version/4.0.5 Safari/531.22.7",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; ko-kr) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; ru-ru) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; zh-cn) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.342.7 Safari/533.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.1 (KHTML, like Gecko) Chrome/6.0.414.0 Safari/534.1",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/8.0.552.210 Safari/534.10",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.0 Safari/534.13",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.0 Safari/534.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.127 Safari/534.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.17 (KHTML, like Gecko) Chrome/11.0.655.0 Safari/534.17",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.2 (KHTML, like Gecko) Chrome/6.0.451.0 Safari/534.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.458.1 Safari/534.3",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.461.0 Safari/534.3",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.464.0 Safari/534.3",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; fr-FR) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.126 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.0 Safari/534.13",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.639.0 Safari/534.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.204",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_6; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.134 Safari/534.16",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_6; en-US) AppleWebKit/534.18 (KHTML, like Gecko) Chrome/11.0.660.0 Safari/534.18",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_6; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_7; en-us) AppleWebKit/533.4 (KHTML, like Gecko) Version/4.1 Safari/533.4",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_7_0; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.342.7 Safari/533.2",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_7_0; en-US) AppleWebKit/534.21 (KHTML, like Gecko) Chrome/11.0.678.0 Safari/534.21",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; da-dk) AppleWebKit/531.22.7 (KHTML, like Gecko) Version/4.0.5 Safari/531.22.7",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; de) AppleWebKit/528.4+ (KHTML, like Gecko) Version/4.0dp1 Safari/526.11.2",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; de-de) AppleWebKit/533.16 (KHTML, like Gecko) Version/4.1 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; en) AppleWebKit/528.4+ (KHTML, like Gecko) Version/4.0dp1 Safari/526.11.2",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; fr) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; hu-hu) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; ja-jp) AppleWebKit/533.16 (KHTML, like Gecko) Version/4.1 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; nl-nl) AppleWebKit/533.16 (KHTML, like Gecko) Version/4.1 Safari/533.16",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_4_11; tr) AppleWebKit/528.4+ (KHTML, like Gecko) Version/4.0dp1 Safari/526.11.2",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_5_7; en-us) AppleWebKit/530.19.2 (KHTML, like Gecko) Version/4.0.2 Safari/530.19",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_5_8; en-us) AppleWebKit/531.22.7 (KHTML, like Gecko) Version/4.0.5 Safari/531.22.7",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_5_8; en-us) AppleWebKit/532.0+ (KHTML, like Gecko) Version/4.0.3 Safari/531.9",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_5_8; en-us) AppleWebKit/532.0+ (KHTML, like Gecko) Version/4.0.3 Safari/531.9.2009",
"Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_5_8; ja-jp) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16"
return {"User-Agent":random.choice(pc_Agent)}
md5.update(txt_msg.encode('utf-8'))
return str(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime()))
async def touch_file(session, img_msg):
file_save_full_path = img_msg[0]
file_url_temp = img_msg[1]['url']
if 'dpic.' in file_url_temp:
file_url = file_url_temp.replace('dpic.', 'pic.').replace('tiankong', 'quanjing')
image_ukey = make_ukey(img_msg[1]['tag']+file_url_temp+img_msg[1]['captions'])
image_name = image_ukey+'.jpg'
file_ok_path = os.path.join(file_save_full_path, image_name)
async with session.get(file_url, headers=change_ua(), timeout=8, verify_ssl=False) as res:
file_content = await res.content.read()
with open(file_ok_path,'wb') as files:
files.write(file_content)
print("download_msgs:" + image_name + ' ' + 'download ok!!!')
except asyncio.TimeoutError:
async with session.get(file_url, headers=change_ua(), timeout=8, verify_ssl=False) as res:
file_content = await res.content.read()
with open(file_ok_path,'wb') as files:
files.write(file_content)
print("download_msgs:" + image_name + ' ' + 'download ok!!!')
except asyncio.TimeoutError:
async with session.get(file_url, headers=change_ua(), timeout=8, verify_ssl=False) as res:
file_content = await res.content.read()
with open(file_ok_path,'wb') as files:
files.write(file_content)
print("download_msgs:" + image_name + ' ' + 'download ok!!!')
except asyncio.TimeoutError:
async def main(small_task_list):
async with aiohttp.ClientSession() as session:
all_tasks = [asyncio.create_task(touch_file(session, img_msg)) for img_msg in small_task_list]
await asyncio.wait(all_tasks)
if __name__ == '__main__':
print('start_time:' + show_time())
base_path = os.path.join(root_path, img_json_folder)
all_json_files = os.listdir(base_path)
for each_json_file in all_json_files:
now_save_folder_path = os.path.join(root_path, each_json_file.replace('.json', ''))
if(not os.path.exists(now_save_folder_path)):
os.makedirs(now_save_folder_path)
json_full_path = os.path.join(base_path, each_json_file)
with open(json_full_path, 'r', encoding='utf8') as task_file:
print("开始下载"+each_json_file)
now_task_list = json.loads(task_file.read())
done_ukey_list_temp += [y.replace('.jpg', '').strip() for y in os.listdir(now_save_folder_path)]
all_task_list += [(now_save_folder_path, each_img_msg) for each_img_msg in now_task_list]
done_ukey_list = set([each_ukey for each_ukey in done_ukey_list_temp if len(each_ukey)>0])
not_crawl_list = [each_task for each_task in all_task_list if make_ukey((each_task[1]['tag']+each_task[1]['url']+each_task[1]['captions'])) not in done_ukey_list]
all_small_task = average_split_task(not_crawl_list, crawl_speed)
for each_small_task in all_small_task:
loop = asyncio.get_event_loop()
loop.run_until_complete(main(each_small_task))
print("over_time:" + show_time())
